Review Special Issues

Few-shot learning based on deep learning: A survey

  • In recent years, with the development of science and technology, powerful computing devices have been constantly developing. As an important foundation, deep learning (DL) technology has achieved many successes in multiple fields. In addition, the success of deep learning also relies on the support of large-scale datasets, which can provide models with a variety of images. The rich information in these images can help the model learn more about various categories of images, thereby improving the classification performance and generalization ability of the model. However, in real application scenarios, it may be difficult for most tasks to collect a large number of images or enough images for model training, which also restricts the performance of the trained model to a certain extent. Therefore, how to use limited samples to train the model with high performance becomes key. In order to improve this problem, the few-shot learning (FSL) strategy is proposed, which aims to obtain a model with strong performance through a small amount of data. Therefore, FSL can play its advantages in some real scene tasks where a large number of training data cannot be obtained. In this review, we will mainly introduce the FSL methods for image classification based on DL, which are mainly divided into four categories: methods based on data enhancement, metric learning, meta-learning and adding other tasks. First, we introduce some classic and advanced FSL methods in the order of categories. Second, we introduce some datasets that are often used to test the performance of FSL methods and the performance of some classical and advanced FSL methods on two common datasets. Finally, we discuss the current challenges and future prospects in this field.

    Citation: Wu Zeng, Zheng-ying Xiao. Few-shot learning based on deep learning: A survey[J]. Mathematical Biosciences and Engineering, 2024, 21(1): 679-711. doi: 10.3934/mbe.2024029

    Related Papers:

    [1] Jingya Wang, Ye Zhu . L2L control for memristive NNs with non-necessarily differentiable time-varying delay. Mathematical Biosciences and Engineering, 2023, 20(7): 13182-13199. doi: 10.3934/mbe.2023588
    [2] Kseniia Kravchuk, Alexander Vidybida . Non-Markovian spiking statistics of a neuron with delayed feedback in presence of refractoriness. Mathematical Biosciences and Engineering, 2014, 11(1): 81-104. doi: 10.3934/mbe.2014.11.81
    [3] Tianqi Yu, Lei Liu, Yan-Jun Liu . Observer-based adaptive fuzzy output feedback control for functional constraint systems with dead-zone input. Mathematical Biosciences and Engineering, 2023, 20(2): 2628-2650. doi: 10.3934/mbe.2023123
    [4] Gonzalo Robledo . Feedback stabilization for a chemostat with delayed output. Mathematical Biosciences and Engineering, 2009, 6(3): 629-647. doi: 10.3934/mbe.2009.6.629
    [5] Linni Li, Jin-E Zhang . Input-to-state stability of stochastic nonlinear system with delayed impulses. Mathematical Biosciences and Engineering, 2024, 21(2): 2233-2253. doi: 10.3934/mbe.2024098
    [6] Xiaoxiao Dong, Huan Qiao, Quanmin Zhu, Yufeng Yao . Event-triggered tracking control for switched nonlinear systems. Mathematical Biosciences and Engineering, 2023, 20(8): 14046-14060. doi: 10.3934/mbe.2023627
    [7] Tong Guo, Jing Han, Cancan Zhou, Jianping Zhou . Multi-leader-follower group consensus of stochastic time-delay multi-agent systems subject to Markov switching topology. Mathematical Biosciences and Engineering, 2022, 19(8): 7504-7520. doi: 10.3934/mbe.2022353
    [8] Dong Xu, Xinling Li, Weipeng Tai, Jianping Zhou . Event-triggered stabilization for networked control systems under random occurring deception attacks. Mathematical Biosciences and Engineering, 2023, 20(1): 859-878. doi: 10.3934/mbe.2023039
    [9] Yue Song, Yi Zhang, Song Yang, Na Li . Investigation on stability and controller design for singular bio-economic systems with stochastic fluctuations. Mathematical Biosciences and Engineering, 2021, 18(3): 2991-3005. doi: 10.3934/mbe.2021150
    [10] Xiaofeng Chen . Double-integrator consensus for a switching network without dwell time. Mathematical Biosciences and Engineering, 2023, 20(7): 11627-11643. doi: 10.3934/mbe.2023516
  • In recent years, with the development of science and technology, powerful computing devices have been constantly developing. As an important foundation, deep learning (DL) technology has achieved many successes in multiple fields. In addition, the success of deep learning also relies on the support of large-scale datasets, which can provide models with a variety of images. The rich information in these images can help the model learn more about various categories of images, thereby improving the classification performance and generalization ability of the model. However, in real application scenarios, it may be difficult for most tasks to collect a large number of images or enough images for model training, which also restricts the performance of the trained model to a certain extent. Therefore, how to use limited samples to train the model with high performance becomes key. In order to improve this problem, the few-shot learning (FSL) strategy is proposed, which aims to obtain a model with strong performance through a small amount of data. Therefore, FSL can play its advantages in some real scene tasks where a large number of training data cannot be obtained. In this review, we will mainly introduce the FSL methods for image classification based on DL, which are mainly divided into four categories: methods based on data enhancement, metric learning, meta-learning and adding other tasks. First, we introduce some classic and advanced FSL methods in the order of categories. Second, we introduce some datasets that are often used to test the performance of FSL methods and the performance of some classical and advanced FSL methods on two common datasets. Finally, we discuss the current challenges and future prospects in this field.



    In many industrial applications, due to the ubiquity of stochastic noise and nonlinear [1,2], real systems are often modelled by stochastic differential equations, which attracts researchers to pay more and more attention to the control of stochastic systems. Using the state-feedback, a closed-loop pole can be arbitrarily configured to improve the performance of the control systems. Therefore, some scholars research the problem of state-feedback stabilization for stochastic systems, e.g., reference [3] focuses on the cooperative control problem of multiple nonlinear systems perturbed by second-order moment processes in a directed topology. Reference [4] considers the case where the diffusion term and the drift term are unknown parameters for stochastic systems with strict feedback. Reference [5] studies stochastic higher-order systems with state constraints and [6] discusses output constrained stochastic systems with low-order and high-order nonlinear and stochastic inverse dynamics. However, it is often difficult to obtain all the state variables of the system directly, it is unsuitable for direct measurement or the measurement equipment is limited in economy and practicality, so the physical implementation of state-feedback is difficult. One of the solutions to this difficulty is to reconstruct the state of the system. At this time, scholars use an observer to investigate the output-feedback stabilization, e.g., reference [7] investigates the prescribed-time stability problem of stochastic nonlinear strict-feedback systems. Reference [8] focuses on stochastic strict feedback systems with sensor uncertainties. In addition, based on output-feedback, for nonlinear multiagent systems, a distributed output-feedback tracking controller is proposed in [9].

    It should be noted that all of the above results [7,8,9], Markovian switching is not considered in the design of output-feedback controller. However, as demonstrated by [10], switching system is a complex hybrid system, which consists of a series of subsystems and switching rules that coordinate the order of each subsystem. In real life, due to the aging of internal components, high temperature, sudden disturbance of external environment, operator error and other inevitable factors, the structure of many systems changes suddenly. Such systems can be reasonably modelled as differential equation with Markovian switching, see [11,12]. Recently, references [13] and [14] discuss the adaptive tracking problem and output tracking problem with Markovian switching respectively. Besides, as shown in [15], the power of the system changes because of factors such as the aging of the springs inside the boiler-turbine unit. Therefore, the research on the stability of stochastic nonlinear systems with time-varying powers has important practical significance. Reference [16] investigates the optimality and stability of high-order stochastic systems with time-varying powers. However, these results do not address the output-feedback stabilization for higher-order stochastic systems with both Markovian switching and time-varying powers.

    Based on these discussions, we aim to resolve the output-feedback stabilization for higher-order stochastic nonlinear systems with both Markovian switching and time-varying powers. The main contributions and characteristics of this paper are two-fold:

    1) The system model we take into account is more applicable than the existing results [7,8,9] and [12,13,14]. Different from the previous results [7,8,9], the stochastic system with Markovian switching is studied in this paper. Unlike previous studies in [12,13,14], we investigate the power is time-varying. The simultaneous existence of the Markov process and time-varying order makes the controller design process more complicated and difficult. More advanced stochastic analysis techniques are needed.

    2) We propose a new observer. The existence of Markovian switching and nondifferentiable time-varying power makes the observer constructed in [7,8,9] invalid. We use the time-varying power's bounds to construct a new observer, which can effectively observe the unmeasurable state and can deal with the nonlinear growth rate, while the existing observer can only deal with constant growth rate.

    The rest of this paper is listed as follows. The problem is formulated in Section 2. In Section 3, an output-feedback controller is designed. Section 4 is the stability analysis. A simulation is given in Section 5. The conclusions are collected in Section 6.

    Notations: R2 denotes the 2-dimensional space and the set of nonnegative real numbers is represented by R+. X denotes the matrix or vector, its transpose is represented by XT. |X| denotes the Euclidean norm of a vector X. When X is square, Tr{X} denotes its trace. The set of all functions with continuous ith partial derivatives is represented by Ci. Let C2,1(R2×R+×S;R+) represent all nonnegative functions V on R2×R+×S which are C2 in x and C1 in t.

    This paper studies the output-feedback stabilization for stochastic nonlinear systems with both Markovian switching and time-varying powers described by:

    dζ1=[ζ2]m(t)dt,dζ2=[u]m(t)dt+fTγ(t)(ˉζ2)dω,y=ζ1, (2.1)

    where ζ=ˉζ2=(ζ1,ζ2)TR2, yR and uR are the system state, control output and the input, respectively. The state ζ2 is unmeasurable. The function m(t):R+R+ is continuous and bounded, which satisfies 1m_m(t)ˉm with m_ and ˉm being constants. The powers sign function []α is defined as []α:=sign()||α with α(0,+). The functions fγ(t) is assumed to be smooth, and for all t0, the locally Lipschitz continuous in x uniformly. fγ(t)(t,0)=0. ω is an rdimensional standard Wiener process, which is defined on the complete probability space (Ω,F,Ft,P) with the filtration Ft satisfying the general conditions. γ(t) is a homogeneous Markov process on the probability space taking values in a space S={1,2,...,N}, which the generator Γ=(λij)N×N given by

    Pij(t)=P{γ(t+s)=i|γ(s)=j}={λijt+o(t)ifij,1+λijt+o(t)ifi=j, (2.2)

    where λij>0 is the transition rate from i to j if ij while λii=ΣNj=1,ijλij for any s,t0. Suppose the Markov process γ(t) is irrelevant to the ω(t).

    To implement the controller design, we need the following assumption.

    Assumption 2.1. There exists a non-negative smooth function ˜f(ζ1) such that

    |fγ(t)(ˉζ2)|(|ζ1|m(t)+12+|ζ2|m(t)+12)˜f(ζ1). (2.3)

    Remark 2.1. As we know, the existing results for stochastic systems with time-varying powers (e.g., [16]), neither the state-feedback control nor the output-feedback control, has considered Markovian switching. However, the structure of many physical systems in the actual system often mutates, which makes it necessary to study systems with both Markovain switching and time-varying powers. Therefore, compared with [16], the model we consider is more practical and more general.

    Remark 2.2. In Assumption 2.1, we can see that the power m(t) is time-varying and the growth rate ˜f(ζ1) is a nonlinear function. When m(t)=1 and ˜f(ζ1) is a constant, Assumption 2.1 is a linear growth condition. However, we consider that ˜f(ζ1) is a nonlinear function, which includes the constant case as a special case. The growth condition of Assumption 2.1 is broader than the linear growth condition. The time-varying power m(t) makes the design in [7,8,9] for time-invariant power invalid. In addition, the nonlinear growth rate ˜f(ζ1) makes the design in [7,8,9,17,18] for constant growth rate fail. A new design scheme should be proposed.

    In this section, we develop an output-feedback controller design for system (2.1). The process is divided into two steps:

    Firstly, we assume that all states are measurable and develop a state-feedback controller using backstepping technique.

    Secondly, we construct a reduced-order observer with a dynamic gain, and design an output-feedback controller.

    In this part, under Assumption 2.1, our objective is to develop a state-feedback controller design for the system (2.1).

    Step 1. Introducing the coordinate transformation ξ1=ζ1 and choosing V1=14ξ41, by using the infinitesimal generator defined in section 1.8 of [11], we have

    LV1ξ31[ζ2]m(t)+IIV1ξ31([ζ2]m(t)[ζ2]m(t))+ξ31[ζ2]m(t)+IIV1. (3.1)

    If we choose ζ2 as

    ζ2=c1/m_1ξ1:=α1ξ1, (3.2)

    we get

    ξ31[ζ2]m(t)=αm(t)1ξm(t)+31c1|ξ1|m(t)+3, (3.3)

    where α1=c1/m_11 is a constant with c11 being a design parameter.

    Substituting (3.3) into (3.1) yields

    LV1c1|ξ1|m(t)+3+ξ31([ζ2]m(t)[ζ2]m(t))+IIV1. (3.4)

    Step 2. Introducing the coordinate transformation ξ2=ζ2ζ2, and using Itô's differentiation rule, we get

    dξ2=([u]m(t)ζ2ζ1[ζ2]m(t))dt+fTγ(t)(ˉζ2)dω. (3.5)

    Choose V2=V1+14ξ42. From (3.4) and (3.5), we obtain

    LV2c1|ξ1|m(t)+3+ξ31([ζ2]m(t)[ζ2]m(t))+ξ32[u]m(t)ξ32ζ2ζ1[ζ2]m(t)+32ξ22|fTγ(t)(ˉζ2)|2+IIV2. (3.6)

    By (3.2) and using Lemma 1 in [19], we have

    ξ31([ζ2]m(t)[ζ2]m(t))ˉm(2ˉm2+2)(|ξ1|3|ξ2|m(t)+αˉm11|ξ1|m(t)+2|ξ2|). (3.7)

    By using Lemma 2.1 in [20], we get

    ˉm(2+2ˉm2)|ξ1|3|ξ2|m(t)16|ξ1|3+m(t)+β211|ξ2|3+m(t),ˉm(2+2ˉm2)αˉm11|ξ1|m(t)+2|ξ2|16|ξ1|3+m(t)+β212|ξ2|3+m(t), (3.8)

    where

    β211=ˉmm_+3(ˉm(2+2ˉm2))3+ˉmm_(3+m_18)3ˉm,β212=1m_+3(ˉm(2+2ˉm2)αˉm11)ˉm+3(m_+36(ˉm+2))(ˉm+2). (3.9)

    Substituting (3.8) into (3.7) yields

    ξ31([ζ2]m(t)[ζ2]m(t))13|ξ1|3+m(t)+β21|ξ2|3+m(t), (3.10)

    where β21=β211+β212 is a positive constant.

    By (3.2) and using Lemma 5 in [21], we get

    |ζ2|m(t)=|ξ2+ζ2|m(t)(|ξ2|+|α1ξ1|)m(t)2ˉm1(|ξ2|m(t)+|α1ξ1|m(t))2ˉm1αˉm1(|ξ2|m(t)+|ξ1|m(t)), (3.11)

    which means that

    |ζ1|m(t)+|ζ2|m(t)φ1(|ξ2|m(t)+|ξ1|m(t)), (3.12)

    where φ1=2ˉm1αˉm1+10 is a constant.

    By (3.11) and using Lemma 1 in [19], we have

    ξ32ζ2ζ1[ζ2]m(t)|ξ32||ζ2ζ1|2ˉm1αˉm1(|ξ2|m(t)+|ξ1|m(t))2ˉm1αˉm1|ζ2ζ1|(|ξ2|m(t)+3+|ξ32||ξ1|m(t)). (3.13)

    By using Lemma 2.1 in [20], we get

    2ˉm1αˉm1|ζ2ζ1||ξ32||ξ1|m(t)13|ξ1|3+m(t)+β221(ζ1)|ξ2|3+m(t), (3.14)

    where

    β221(ζ1)=3m_+3(2ˉm1αˉm1|ζ2ζ1|)ˉm+33(m_+33ˉm)ˉm3. (3.15)

    Substituting (3.14) into (3.13) yields

    ξ32ζ2ζ1[ζ2]m(t)13|ξ1|3+m(t)+β22(ζ1)|ξ2|3+m(t), (3.16)

    where β22(ζ1)=2ˉm1αˉm1|ζ2ζ1|+β221(ζ1) is a smooth function irrelevant to m(t).

    By (3.12), using Assumption 2.1 and Lemma 1 in [19], we get

    32ξ22|fTγ(t)(ˉζ2)|23˜f2(ζ1)|ξ2|2(|ζ1|m(t)+1+|ζ2|m(t)+1)3˜f2(ζ1)φ2(|ξ2|m(t)+3+|ξ2|2|ξ1|m(t)+1), (3.17)

    where φ2=2ˉmαˉm+11+10 is a constant.

    From Lemma 2.1 in [20], we obtain

    3˜f2(ζ1)φ2|ξ2|2|ξ1|m(t)+113|ξ1|m(t)+3+β231(ζ1)|ξ2|m(t)+3, (3.18)

    where

    β231(ζ1)=2m_+3(3˜f2(ζ1)φ2)ˉm+32(m_+33(ˉm+1))ˉm+12. (3.19)

    Substituting (3.18) into (3.17) yields

    32ξ22|fTγ(t)(ˉζ2)|213|ξ1|m(t)+3+β23(ζ1)|ξ2|m(t)+3, (3.20)

    where β23(ζ1)=3˜f2(ζ1)φ2+β231(ζ1)0 is a smooth function irrelevant to m(t).

    By using (3.6), (3.10), (3.16) and (3.20), we obtain

    LV2(c11)|ξ1|m(t)+3+ξ32([u]m(t)[x3]m(t))+ξ32[x3]m(t)+β2(ζ1)|ξ2|m(t)+3+IIV2, (3.21)

    where β2(ζ1)=β21(ζ1)+β22(ζ1)+β23(ζ1) is a smooth function irrelevant to m(t).

    Constructing the virtual controller as

    x3=(c2+β2(ζ1))1m_:=α2(ζ1)ξ2, (3.22)

    we have

    ξ32[x3]m(t)=αm(t)2(ζ1)ξm(t)+32(c2+β2(ζ1))ξm(t)+32, (3.23)

    where c2>0 is a constant and α2(ζ1)0 is a smooth function irrelevant to m(t).

    Substituting (3.23) into (3.21) yields

    LV2(c11)|ξ1|m(t)+3c2|ξ2|m(t)+3+ξ32([u]m(t)[x3]m(t))+IIV2. (3.24)

    In this part, we first design a reduced-order observer with a dynamic gain, then we design an output-feedback controller.

    Since ζ2 are unmeasurable, we construct the following observer

    dη=([u]m(t)L(ζ1)ζ1[η+L(ζ1)]m(t))dt, (3.25)

    where L(ζ1) is a smooth function, and L(ζ1)ζ1>0 is irrelevant to m(t).

    Defining e=ζ2L(ζ1)η and by the construction of the observer, we have

    de=L(ζ1)ζ1([η+L(ζ1)]m(t)[ζ2]m(t))dt+fTγ(t)(ˉζ2)dω. (3.26)

    Choose U=14e4. From (3.26), we get

    LU=e3L(ζ1)ζ1([η+L(ζ1)]m(t)[ζ2]m(t))+32e2|fTγ(t)(ˉζ2)|2+IIU. (3.27)

    By definition of e and lemma 2.2 in [22], we have

    e3L(ζ1)ζ1([η+L(ζ1)]m(t)[ζ2]m(t))12ˉm1L(ζ1)ζ1em(t)+3. (3.28)

    From (3.12), (3.17) and Assumption 2.1, we get

    32e2|fTγ(t)(ˉζ2)|23˜f2(ζ1)|e|2(|ζ1|m(t)+1+|ζ2|m(t)+1)3˜f2(ζ1)φ2(|e|2|ξ2|m(t)+1+|e|2|ξ1|m(t)+1). (3.29)

    By using Lemma 2.1 in [20], we have

    3˜f2(ζ1)φ2|e|2|ξ1|1+m(t)|ξ1|3+m(t)+β31(ζ1)|e|3+m(t),3˜f2(ζ1)φ2|e|2|ξ2|1+m(t)12|ξ2|3+m(t)+β32(ζ1)|e|3+m(t), (3.30)

    where

    β31(ζ1)=2m_+3(3˜f2(ζ1)φ2)ˉm+32(m_+3ˉm+1)ˉm+12,β32(ζ1)=2m_+3(3˜f2(ζ1)φ2)ˉm+32(3+m_2(1+ˉm))1+ˉm2. (3.31)

    Substituting (3.30) into (3.29) yields

    32e2|fTγ(t)(ˉζ2)|2|ξ1|m(t)+3+12|ξ2|m(t)+3+β3(ζ1)|e|m(t)+3, (3.32)

    where β3(ζ1)=β31(ζ1)+β32(ζ1)0 is a smooth function irrelevant to m(t).

    Substituting (3.28), (3.32) into (3.27) yields

    LU|ξ1|m(t)+3+12|ξ2|m(t)+3(12ˉm1L(ζ1)ζ1β3(ζ1))|e|m(t)+3+IIU. (3.33)

    Since ζ2 is unmeasurable, replace ζ2 in virtual controller x3 with η+L(ζ1), and we can get the controller as follows

    u=α2(ζ1)(η+L(ζ1)+α1ζ1). (3.34)

    By (3.22), (3.24) and (3.34), we obtain

    LV2(c11)|ξ1|m(t)+3c2|ξ2|m(t)+3+ξ32αˉm2(ζ1)([ξ2]m(t)[ξ2e]m(t))+IIV2. (3.35)

    By using Lemma 1 in [19], we have

    ξ32αˉm2(ζ1)([ξ2]m(t)[ξ2e]m(t))αˉm2(ζ1)ˉm(2ˉm2+2)(|ξ2|3|e|m(t)+|e||ξ2|m(t)+2). (3.36)

    By using Lemma 2.1 in [20], we get

    αˉm2(ζ1)ˉm(2ˉm2+2)|ξ2|3|e|m(t)14|ξ2|3+m(t)+β41(ζ1)|e|3+m(t),αˉm2(ζ1)ˉm(2ˉm2+2)|e||ξ2|2+m(t)14|ξ2|3+m(t)+β42(ζ1)|e|3+m(t), (3.37)

    where

    β41(ζ1)=ˉmm_+3(αˉm2(ζ1)ˉm(2ˉm2+2))ˉm+3m_(m_+312)3ˉm,β42(ζ1)=1m_+3(αˉm2(ζ1)ˉm(2ˉm2+2))ˉm+3(m_+34(ˉm+2))(ˉm+2). (3.38)

    Substituting (3.37) into (3.36) yields

    ξ32αˉm2(ζ1)([ξ2]m(t)[ξ2e]m(t))12|ξ2|3+m(t)+β4(ζ1)|e|3+m(t), (3.39)

    where β4(ζ1)=β41(ζ1)+β42(ζ1)0 is a smooth function irrelevant to m(t).

    By using (3.39) and (3.35), we have

    LV2(c11)|ξ1|m(t)+3(c212)|ξ2|m(t)+3+β4(ζ1)|e|m(t)+3+IIV2. (3.40)

    Choosing V(ξ1,ξ2,e)=V2(ξ1,ξ2)+U(e), by (3.33) and (3.40), we obtain

    LV(c12)|ξ1|m(t)+3(c21)|ξ2|m(t)+3(12ˉm1L(ζ1)ζ1β3(ζ1)β4(ζ1))|e|m(t)+3+IIV. (3.41)

    Let

    L(ζ1)=12ˉm1(c3ζ1+ζ10(β3(s)+β4(s))ds), (3.42)

    and the controller as

    u=α2(ζ1)(η+12ˉm1(c3ζ1+ζ10(β3(s)+β4(s))ds)+α1ζ1), (3.43)

    where c3>0 is a design parameter.

    By using (3.41) and (3.42), we can obtain

    LV(c12)|ξ1|m(t)+3(c21)|ξ2|m(t)+3c3|e|m(t)+3+IIV. (3.44)

    Remark 3.1. If m(t) is time-invariant and the growth rate is a constant rather than a smooth function, such as those in [7,8,9], from (3.32) and (3.39), β3 and β4 are constants irrelevant to ζ1. Then, the dynamic gain L(ζ) is a linear function of ζ1. We can design L(ζ1)=cζ1 by choosing the right parameter c to make LV in (3.41) negative definite. However, in this paper, the growth rate ˜f(ζ1) is a nonnegative smooth function and the m(t) is time-varying and non-differentiable, which makes the deducing of the dynamic gain much more difficult. To solve this problem, we introduce two constants m_ and ˉm, which are reasonably used in the design process, see (3.7) and (3.11). In this way, the dynamic gain (3.42) can be designed irrelevant to m(t), which is crucial to assure the effectiveness of the observer and controller. This is one of the main innovations of this paper.

    In this section, for the closed-loop system (2.1), (3.25) and (3.43), we first give a lemma, which is useful to prove the system has a unique solution. Then, we present the main results of the stability analysis.

    Lemma 4.1. For ζR, the function g(ζ)=[ζ]m(t) satisfies the locally Lipschitz condition.

    Proof. If ζ=0, we can get

    h+(0)=limζ0+h(ζ)h(0)ζ=0,h(0)=limζ0h(ζ)h(0)ζ=0. (4.1)

    Then, we have

    dhdζ|ζ=0=h+(0)=h(0)=0, (4.2)

    thus, h(ζ) is differentiable function in ζ=0 and so meets the locally Lipschitz condition in ζ=0.

    As ζ>0, we get

    h(ζ)=[ζ]m(t)=ζm(t). (4.3)

    For m(t)1, h(ζ) is differentiable function in ζ>0, so meets the locally Lipschitz condition in ζ>0. Similarly, as ζ<0, the conclusion is valid.

    Therefore, the conclusion holds for ζR.

    Next, we give the stability results.

    Theorem 4.1. Under Assumption 2.1, for the system (2.1), using the observer (3.25) and controller (3.43) with

    ci>3i,i=1,2,3, (4.4)

    we can get

    1) For each ζ(t0)=ζ0R2 and γ(t0)=i0S, the closed-loop system has an almost surely unique solution on [0,+);

    2) For any ζ0R2 and i0S, the closed-loop system is almost surely regulated to the equilibrium at the origin.

    Proof. By (2.1), (3.25), (3.43) and using Lemma 4.1, we can conclude that the closed-loop system satisfies the locally Lipschitz condition. By (3.2), (3.22), (3.25) and (3.42), we can get that ξ1,ξ2,η are bounded, which implies that ζ1 is bounded, which means that

    VR=inftt0,|ζ|>RV(ζ(t))R. (4.5)

    Through the verification of the controller development process, we choose appropriate design parameters ci to satisfy (4.4), and we can get IIV=0. For each l>0, the first exit time is defined as

    σl=inf{t:tt0,|ζ(t)|l}. (4.6)

    When tt0, choose tl=min{σl,t}. We can obtain that bounded |ζ(t)| on interval [t0,tl] a.s., which means that V(ζ) is bounded in the interval [t0,tl] a.s. By using (3.44), we can get that LV is bounded in the interval [t0,tl] a.s. By using Lemma 1.9 in [11], (3.44) and (4.4), we can obtain

    EV(ζ(tl))EV(ζ(t0)). (4.7)

    By (4.5), (4.7) and using Lemma 1 in [23], we can obtain conclusion (1).

    From (3.44), (4.5), by using Theorem 2.1 in [24], we can prove conclusion (2).

    In this section, a simulation example is given to show the availability of the control method.

    Study the stabilization for system with two modes. The Markov process γ(t) belongs to the space S={1,2} with generator Γ=(λij)2×2 given by λ11=2,λ12=2,λ21=1 and λ22=1. We have π1=13,π2=23. When γ(t)=1, the systems can be written as

    dζ1=[ζ2]32+12sintdt,dζ2=[u]32+12sintdt+ζ1sinζ2dω,y=ζ1, (5.1)

    where m(t)=32+12sint,m_=1,ˉm=2. When γ(t)=2, the systems are described by

    dζ1=[ζ2]2+sintdt,dζ2=[u]2+sintdt+12ζ21sinζ2dω,y=ζ1, (5.2)

    where m(t)=2+sint,m_=1,ˉm=3. Clearly, system (5.1) and (5.2) satisfy Assumption 2.1.

    According to the above design process, when γ(t)=1, the observer is constructed as

    dη=([u]32+12sintL(ζ1)ζ1[η+L(ζ1)]32+12sint)dt, (5.3)

    and the control is

    u=(c2+4ζ21)(η+L(ζ1)+c1ζ1), (5.4)

    where L(ζ1)=12(c3ζ1+6ζ21).

    When γ(t)=2, the observer is constructed as

    dη=([u]2+sintL(ζ1)ζ1[η+L(ζ1)]2+sint)dt, (5.5)

    and the control is

    u=(c2+4ζ1+12ζ21)(η+L(ζ1)+c1ζ1), (5.6)

    where L(ζ1)=14(c3ζ1+20ζ1+4ζ21).

    For simulation, we select c1=6,c2=6,c3=5, and the initial conditions as ζ1(0)=1,ζ2(0)=2,η(0)=5. We can obtain Figure 1, which illustrates that the signals of the closed-loop system (ζ1,ζ2,u,η,e) converge to zero. Specifically, the states and controller of the closed-loop system converge to zero. The observation error also converges to zero, which means that our constructed observer and controller are efficient. Figure 2 illustrates the jump of Markov process γ(t) in 1 and 2.

    Figure 1.  The responses of closed-loop systems (5.1)--(5.6).
    Figure 2.  The runs of the Markov process γ(t).

    Remark 5.1. It can be observed from the example that there are time-varying powers and Markovian switching in systems (5.1) and (5.2). For the output-feedback control of the system (5.1) and (5.2), the method in [7,8,9] fails since they can only deal with time-invariant powers without Markovian switching. To solve the difficulties caused by time-varying powers, we introduce constants 1, 2, and 1, 3 so that the design of the observer and controller is irrelevant to the power. This is one of the characteristics of our controller and observer design scheme (5.3)–(5.6).

    We investigate the output-feedback stabilization for stochastic nonlinear systems with both Markovian switching and time-varying powers in this paper. Compared with existing work, the system model considered in this paper is more general because it studies the time-varying power and Markovian switching, simultaneously. To achieve stabilization, we first design a state observer with a dynamic gain and an output-feedback controller, then use advanced stochastic analysis techniques to prove that the closed-loop system has an almost surely unique solution and the states are regulated to the origin almost surely. Even though there is no Markovian switching, the results in this paper are also new in the sense that we consider nonlinear growth rate, which is much more general than constant growth rate cases in [7,8,9].

    There are many related problems to be considered, such as how to extend the result to impulsive systems [25,26,27] and systems with arbitrary order.

    This work is funded by Shandong Province Higher Educational Excellent Youth Innovation team, China (No. 2019KJN017), and Shandong Provincial Natural Science Foundation for Distinguished Young Scholars, China (No. ZR2019JQ22).

    The authors declare there is no conflict of interest.



    [1] H. E. Kim, A. Cosa-Linan, N. Santhanam, M. Jannesari, M. E. Maros, T. Ganslandt, Transfer learning for medical image classification: A literature review, BMC Med. Imaging, 22 (2022), 69. https://doi.org/10.1186/s12880-022-00793-7 doi: 10.1186/s12880-022-00793-7
    [2] Z. X. Zou, K. Y. Chen, Z. W. Shi, Y. H. Guo, J. P. Ye, Object detection in 20 years: A survey, Proc. IEEE, 111 (2023), 257–276. https://doi.org/10.1109/JPROC.2023.3238524 doi: 10.1109/JPROC.2023.3238524
    [3] H. Q. Zhao, W. B. Zhou, D. D. Chen, T. Y. Wei, N. H. Yu, Multi-attentional deepfake detection, in 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE 8 (2021), 2185–2194. https://doi.org/10.1109/CVPR46437.2021.00222
    [4] I. Goodfellow, P. A. Jean, M. Mirza, B. Xu, D. Warde-Farley, S. Ozair, et al., Generative adversarial nets, in Advances in Neural Information Processing Systems, 27 (2014), 1–9.
    [5] B. Pandey, D. K. Pandey, B. P. Mishra, W. Rhmann, A comprehensive survey of deep learning in the field of medical imaging and medical natural language processing: Challenges and research directions, J. King Saud Univ. Comput. Inf. Sci., 34 (2022), 5083–5099. https://doi.org/10.1016/j.jksuci.2021.01.007 doi: 10.1016/j.jksuci.2021.01.007
    [6] P. Li, X. H. Xu, Recurrent compressed convolutional networks for short video event detection, in IEEE Access, 8 (2020), 114162–114171. https://doi.org/10.1109/ACCESS.2020.3003939
    [7] P. Li, Q. H. Ye, L. M. Zhang, L.Yuan, X. H. Xu, L. Shao, Exploring global diverse attention via pairwise temporal relation for video summarization, Pattern Recogn., 111 (2021), 107677. https://doi.org/10.1016/j.patcog.2020.107677 doi: 10.1016/j.patcog.2020.107677
    [8] P. Li, P. Zhang, T. Wang, H. X. Xiao, Time–frequency recurrent transformer with diversity constraint for dense video captioning, Inform. Process. Manag., 60 (2023), 103204. https://doi.org/10.1016/j.ipm.2022.103204 doi: 10.1016/j.ipm.2022.103204
    [9] P. Li, J. C. Cao, L. Yuan, Q. H. Ye, X. H. Xu, Truncated attention-aware proposal networks with multi-scale dilation for temporal action detection, Pattern Recogn., 142 (2023), 109684. https://doi.org/10.1016/j.patcog.2023.109684 doi: 10.1016/j.patcog.2023.109684
    [10] P. Li, Y. Zhang a, L. Yuan, H. X. Xiao, B. B. Lin, X. H. Xu, Efficient long-short temporal attention network for unsupervised video object segmentation, Pattern Recogn., 146 (2024), 110078. https://doi.org/10.1016/j.patcog.2023.110078 doi: 10.1016/j.patcog.2023.110078
    [11] K. Feng, J. C. Ji, Y. C. Zhang, Q. Ni, Z. Liu, M. Beer, Digital twin-driven intelligent assessment of gear surface degradation, Mechan. Syst. Signal Process., 186 (2023), 109896. https://doi.org/10.1016/j.ymssp.2022.109896 doi: 10.1016/j.ymssp.2022.109896
    [12] Y. D. Xu, K. Feng, X. A. Yan, R. Q. Yan, Q. Ni, B. B. Sun, et al., CFCNN: A novel convolutional fusion framework for collaborative fault identification of rotating machinery, Inform. Fusion, 95 (2023), 1–16. https://doi.org/10.1016/j.inffus.2023.02.012 doi: 10.1016/j.inffus.2023.02.012
    [13] K. Feng, Y. D. Xu, Y. L. Wang, S. Li, Q. B. Jiang, B. B. Sun, et al., Digital twin enabled domain adversarial graph networks for bearing fault diagnosis, in IEEE Transactions on Industrial Cyber-Physical Systems, 1 (2023), 113–122. https://doi.org/10.1109/TICPS.2023.3298879
    [14] O. Russakovsky, J. Deng, H. Su, J. Krause, S. Satheesh, S. Ma, et al., ImageNet large scale visual recognition challenge, Int J Comput Vis, 115 (2015), 211–252. https://doi.org/10.1007/s11263-015-0816-y doi: 10.1007/s11263-015-0816-y
    [15] K. M. He, X. Y. Zhang, S. Q. Ren, J. Sun, Deep residual learning for image recognition, in 2016 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, (2016), 770–778. https://doi.org/10.1109/CVPR.2016.90
    [16] A. G. Howard, M. L. Zhu, B. Chen, D. Kalenichenko, W. J. Wang, T. Weyand, et al., MobileNets: Efficient convolutional neural networks for mobile vision applications, preprint, arXiv: 1704.04861.
    [17] X. Y. Zhang, X. Y. Zhou, M. X. Lin, J. Sun, ShuffleNet: An extremely efficient convolutional neural network for mobile devices, in 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, (2018), 6848–6856. https://doi.org/10.1109/CVPR.2018.00716
    [18] G. Huan, Z. Liu, L. V. D. Maaten, K. Q. Weinberger, Densely connected convolutional networks, in 2017 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, (2017), 2261–2269. https://doi.org/10.1109/CVPR.2017.243
    [19] W. H. Yu, M. Luo, P. Zhou, C. Y. Si, Y. C. Zhou, X. C. Wang, et al., MetaFormer is actually what you need for vision, in 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, (2022), 10809–10819. https://doi.org/10.1109/CVPR52688.2022.01055
    [20] Y. P. Chen, X. Y. Dai, D. D. Chen, M. C. Liu, X. Dong, L. Yuan, et al., Mobile-former: Bridging mobilenet and transforme, in 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, (2022), 5270–5279. https://doi.org/10.1109/CVPR52688.2022.00520
    [21] Y. T. Vuong, Q. M. Bui, H. Nguyen, T. Nguyen, V. Tran, X. Phan, et al., SM-BERT-CR: A deep learning approach for case law retrieval with supporting model, Artif. Intell. Law, 31 (2023), 601–628. https://doi.org/10.1007/s10506-022-09319-6 doi: 10.1007/s10506-022-09319-6
    [22] J. Deng, W. Dong, R. Socher, L. J. Li, K. Li, F. F. Li, ImageNet: A large-scale hierarchical image database, in 2009 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, (2009), 248–255. https://doi.org/10.1109/CVPR.2009.5206848
    [23] T. Y. Lin, M. Maire, S. Belongie, J. Hays, P. Perona, D. Ramanan, et al., Microsoft COCO: Common objects in context, in 2014 European conference computer vision (ECCV), (2014), 740–755. https://doi.org/10.1007/978-3-319-10602-1_48
    [24] J. C. Yang, X. L. Guo, Y. Li, F. Marinello, S. Ercisli, Z. Zhang, A survey of few-shot learning in smart agriculture: developments, applications and challenges, Plant Methods., 18 (2022), 28. https://doi.org/10.1186/s13007-022-00866-2 doi: 10.1186/s13007-022-00866-2
    [25] J. D. Chen, J. X. Chen, D.F. Zhang, Y. D. Sun, Y. A. Nanehkaran, Using deep transfer learning for image-based plant disease identification, Comput. Electron. Agri., 173 (2020), 105393. https://doi.org/10.1016/j.compag.2020.105393 doi: 10.1016/j.compag.2020.105393
    [26] S. Q. Jiang, W. Q. Min, Y. Q. Lyu, L. H. Liu, Few-shot food recognition via multi-view representation learning, ACM Transact. Multi. Comput. Commun. Appl., 16 (2020), 1–20. https://doi.org/10.1145/3391624 doi: 10.1145/3391624
    [27] J. Yang, X. M. Wang, Z. P. Luo, Few-shot remaining useful life prediction based on meta-learning with deep sparse kernel network, Inform. Sci., 653 (2024), 119795. https://doi.org/10.1016/j.ins.2023.119795 doi: 10.1016/j.ins.2023.119795
    [28] Y. Q. Wang, Q. M. Yao, J. T. Kwok, L. M. Ni, Generalizing from a few examples: A survey on few-shot learning, ACM Comput. Surveys, 53 (2020), 1–34. https://doi.org/10.1145/3386252 doi: 10.1145/3386252
    [29] J. Lu, P. H. Gong, J. P. Ye, C. H. Zhang, Learning from very few samples: A survey, preprint, arXiv: 2009.02653.
    [30] X. X. Li, X. C. Yang, Z. Y. Ma, J. H. Xue, Deep metric learning for few-shot image classification: A Review of recent developments, Pattern Recogn., 138 (2023), 109381. https://doi.org/10.1016/j.patcog.2023.109381 doi: 10.1016/j.patcog.2023.109381
    [31] A. Dabouei, S. Soleymani, F. Taherkhani, N. M. Nasrabadi, SuperMix: Supervising the mixing data augmentation, in 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, (2021), 13789–13798. https://doi.org/10.1109/CVPR46437.2021.01358
    [32] M. Hong, J. Choi, G. Kim, StyleMix: Separating content and style for enhanced data augmentation, in 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, (2021), 14857–14865. https://doi.org/10.1109/CVPR46437.2021.01462
    [33] N. E. Khalifa, M. Loey, S. Mirjalili, A comprehensive survey of recent trends in deep learning for digital images augmentation, Artif. Intell. Rev., 55 (2022), 2351–2377. https://doi.org/10.1007/s10462-021-10066-4 doi: 10.1007/s10462-021-10066-4
    [34] E. D. Ubuk, B. Zoph, D. Mané, V. Vasudevan, Q. V. Le, AutoAugment: learning augmentation strategies from data, in 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, (2021), 113–123. https://doi.org/10.1109/CVPR.2019.00020
    [35] T. DeVries, G. W. Taylor, Improved regularization of convolutional neural networks with cutout, preprint, arXiv: 1708.04552.
    [36] J. Y. Zhu, T. Park, P. Isola, A. A. Efros, Unpaired image-to-image translation using cycle-consistent adversarial networks, in 2017 IEEE International Conference on Computer Vision (ICCV), IEEE, (2017), 2242–2251. https://doi.org/10.1109/ICCV.2017.244
    [37] T. Karras, T. Aila, S. Laine, J. Lehtinen, Progressive growing of GANs for improved quality, stability and variation, preprint, arXiv: 1710.10196.
    [38] Z. T. Chen, Y. W. Fu, Y. X. Wang, L. Ma, W. Liu, M. Hebert, Image deformation meta-networks for one-Shot learning, in 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, (2019), 8672–8681. https://doi.org/10.1109/CVPR.2019.00888
    [39] S. Yun, D. Han, S. Chun, S. J. Oh, S. Chun, J. Choe, Y. Yoo, CutMix: Regularization strategy to train strong classifiers with localizable features, in 2019 IEEE/CVF International Conference on Computer Vision (ICCV), IEEE, (2019), 6022–6031. https://doi.org/10.1109/ICCV.2019.00612
    [40] S. Khodadadeh, L. Boloni, M. Shah, Unsupervised meta-learning for few-shot image classification, in 2019 Advances in Neural Information Processing Systems (NIPS), (2019).
    [41] A. Antoniou, A. Storkey, Assume, augment and learn: Unsupervised few-shot meta-learning via random labels and data augmentation, preprint, arXiv: 1902.09884.
    [42] T. X. Qin, W. B. Li, Y. H. Shi, Y. Gao, Diversity helps: Unsupervised few-shot learning via distribution shift-based data augmentation, preprint, arXiv: 2004.05805.
    [43] H. Xu, J. X. Wang, H. Li, D. Q. Ouyang, J. Shao, Unsupervised meta-learning for few-shot learning, Pattern Recogn., 116 (2021), 107951. https://doi.org/10.1016/j.patcog.2021.107951 doi: 10.1016/j.patcog.2021.107951
    [44] M. Tao, H. Tang, F. Wu, X. Y. Jing, B. K. Bao, C. S. Xu, DF-GAN: A simple and effective baseline for text-to-image synthesis, in 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, (2022), 16494–16504. https://doi.org/10.1109/CVPR52688.2022.01602
    [45] W. T. Liao, K. Hu, M. Y. Yang, B. Rosenhahn, Text to image generation with semantic-spatial aware GAN, in 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, (2022), 18166–18175. https://doi.org/10.1109/CVPR52688.2022.01765
    [46] X. T. Wu, H. B. Zhao, L. L. Zheng, S. H. Ding, X. Li, Adma-GAN: Attribute-driven memory augmented GANs for text-to-image generation, in Proceedings of the 30th ACM International Conference on Multimedia, ACM, (2022), 1593–1602. https://doi.org/10.1145/3503161.3547821
    [47] A. Mehrotra, A. Dukkipati, Generative adversarial residual pairwise networks for one shot learning, preprint, arXiv: 1703.08033.
    [48] Y. X. Wang, R. Girshick, M. Hebert, B. Hariharan, Low-shot learning from imaginary data, in 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, (2018), 7278–7286. https://doi.org/10.1109/CVPR.2018.00760
    [49] R. X. Zhang, T. Che, Z. Ghahramani, Y. Bengio, Y. Q. Song, MetaGAN: An adversarial approach to few-Shot learning, in 2018 Advances in Neural Information Processing Systems (NIPS), (2018).
    [50] E. Schwartz, L. Karlinsky, J. Shtok, S. Harary, M. Marder, A. Kumar, et al., Delta-encoder: an effective sample synthesis method for few-shot object recognition, in 2018 Advances in Neural Information Processing Systems (NIPS), (2018).
    [51] Y. Q. Xian, S. Sharma, B. Schiele, Z. Akata, F-VAEGAN-D2: A Feature generating framework for any-shot learning, in 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, (2019), 10267–102765. https://doi.org/10.1109/CVPR.2019.01052
    [52] K. Li, Y. L. Zhang, K. P. Li, Y. Fu, Adversarial feature hallucination networks for few-shot learning, in 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, (2020), 13467–13476. https://doi.org/10.1109/CVPR42600.2020.01348
    [53] F. Pahde, P. Jähnichen, T. Klein, M. Nabi, Cross-modal hallucination for few-shot fine-grained recognition, preprint, arXiv: 1806.05147.
    [54] M. Dixit, R. Kwitt, M. Niethammer, N. Vasconcelos, AGA: Attribute-guided augmentation, in 2017 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, (2017), 3328–3336. https://doi.org/10.1109/CVPR.2017.355
    [55] B. Liu, X. D. Wang, M. Dixit, R. Kwitt, N. Vasconcelos, Feature space transfer for data augmentation, in 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, (2018), 9090–9098. https://doi.org/10.1109/CVPR.2018.00947
    [56] Z. T. Chen, Y. W. Fu, Y. D. Zhang, Y. G. Jiang, X. Y. Xue, L. Sigal, Multi-level semantic feature augmentation in few-shot learning, preprint, arXiv: 1804.05298.
    [57] H. G. Zhang, J. Zhang, P. Koniusz, Few-shot learning via saliency-guided hallucination of samples, in 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, (2019), 2765–2774. https://doi.org/10.1109/CVPR.2019.00288
    [58] G. Koch, R. Zemel, R. Salakhutdinov, Siamese neural networks for one-shot image recognition, in 2015 International Conference on Machine Leaning (ICML), (2015).
    [59] O. Vinyals, C. Blundell, T. Lillicrap, K. Kavukcuoglu, D. Wierstra, Matching networks for one shot learning, in 2019 Advances in Neural Information Processing Systems (NIPS), (2019).
    [60] J. Snell, K. Swersky, R. Zemel, Prototypical networks for few-shot learning, in 2017 Advances in Neural Information Processing Systems (NIPS), (2017).
    [61] F. Sung, Y. X. Yang, Li, Zhang, T. Xiang, P. H.S. Torr, T. M. Hospedales, Learning to compare: Relation network for few-shot learning, in 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, (2018), 1199–1208. https://doi.org/10.1109/CVPR.2018.00131
    [62] W. B. Li, L. Wang, J. L. Xu, J. Huo, Y. Gao, J. B. Luo, Revisiting local descriptor based image-to-class measure for few-shot learning, in 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, (2019), 7253–7260. https://doi.org/10.1109/CVPR.2019.00743
    [63] Y. B. Liu, J. H. Lee, M. Park, S. Kim, E. Yang, S. J. Hwang, et al., Learning to propagate labels: Transductive propagation network for few-shot learning, preprint, arXiv: 1805.10002.
    [64] C. Simon, P. Koniusz, R. Nock, M. Harandi, Adaptive Subspaces for Few-Shot Learning, in 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, (2020), 4135–4144. https://doi.org/10.1109/CVPR42600.2020.00419
    [65] K. Allen, E. Shelhamer, H. Shin, J. Tenenbaum, Infinite mixture prototypes for few-shot learning, in 2019 International Conference on Machine Leaning (ICML), (2019), 232–241.
    [66] C. Xing, N. Rostamzadeh, B. Oreshkin, P. O. O. Pinheiro, Adaptive cross-modal few-shot learning, in 2019 Advances in Neural Information Processing Systems (NIPS), (2019).
    [67] X. M. Li, L. Q. Yu, C. W. Fu, M. Fang, P.-A. Heng, Revisiting metric learning for few-shot image classification, Neurocomputing, 406 (2020), 49–58. https://doi.org/10.1016/j.neucom.2020.04.040 doi: 10.1016/j.neucom.2020.04.040
    [68] S. P. Yan, S. Y. Zhang, X. M. He, A dual attention network with semantic embedding for few-shot learning, in 2019 Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), (2019), 9079–9086. https://doi.org/10.1609/aaai.v33i01.33019079
    [69] P. Li, G. P. Zhao, X. H. Xu, Coarse-to-fine few-shot classification with deep metric learning, Inform.n Sci., 610 (2022), 592–604. https://doi.org/10.1016/j.ins.2022.08.048 doi: 10.1016/j.ins.2022.08.048
    [70] T. Y. Gao, X. Han, Z. Y. Liu, M. S. Sun, Hybrid attention-based prototypical networks for noisy few-shot relation classification, in 2019 Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), (2019), 6407–6414. https://doi.org/10.1609/aaai.v33i01.33016407
    [71] B. Oreshkin, P. R. López, A. Lacoste, Tadam: Task dependent adaptive metric for improved few-shot learning, in 2018 Advances in Neural Information Processing Systems (NIPS), (2018)
    [72] H. Y. Li, D. Eigen, S. Dodge, M. Zeiler, X. G. Wang, Finding task-relevant features for few-shot learning by category traversal, in 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, (2019), 1–10. https://doi.org/10.1109/CVPR.2019.00009
    [73] F. Y. Yang, R. P. Wang, X. L. Chen, SEGA: Semantic guided attention on visual prototype for few-shot learning, in 2022 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), IEEE, (2022), 1586–1596. https://doi.org/10.1109/WACV51458.2022.00165
    [74] R. B. Hou, H. Chang, B. P. Ma, S. G. Shan, X. L. Chen, Cross attention network for few-shot classification, in 2019 Advances in Neural Information Processing Systems (NIPS), (2019).
    [75] A. Santoro, S. Bartunov, M. Botvinick, D. Wierstra, T. Lillicrap, One-shot with memory-augmented neural networks, preprint, arXiv: 1605.06065.
    [76] C. Finn, P. Abbeel, S. Levine, Model-agnostic meta-learning for fast adaptation of deep networks, in 2017 International Conference on Machine Leaning (ICML), (2017), 1126–1135.
    [77] A. Nichol, J. Achiam, J. Schulman, On first-order meta-learning algorithms, preprint, arXiv: 1803.02999.
    [78] A. Antoniou, H. Edwards, A. Storkey, How to train your MAML, preprint, arXiv: 1810.09502.
    [79] S. Ravi, H. Larochelle, Optimization as a model for few-shot learning, in 2017 International Conference on Learning Representations (ICLR), (2017)
    [80] S. Gidaris, N. Komodakis, Dynamic few-shot visual learning without forgetting, in 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, (2018), 4367–4375. https://doi.org/10.1109/CVPR.2018.00459
    [81] Q. R. Sun, Y. Y. Liu, T. S. Chua, B. Schiele, Meta-transfer learning for few-shot learning, in 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, (2019), 403–412. https://doi.org/10.1109/CVPR.2019.00049
    [82] H. J. Ye, H. X. Hu, D. C. Zhan, F. Sha, Few-shot learning via embedding adaptation with set-to-set functions, in 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, (2020), 8805–8814. https://doi.org/10.1109/CVPR42600.2020.00883
    [83] K. Lee, S. Maji, A. Ravichandran, S. Soatto, Meta-learning with differentiable convex optimization, in 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, (2019), 10649–10657. https://doi.org/10.1109/CVPR.2019.01091
    [84] C. Zhang, H. H. Ding, G. S. Lin, R. B. Li, C. H. Wang, C. H. Shen, Meta navigator: Search for a Good Adaptation Policy for Few-shot Learning, in 2021 IEEE/CVF International Conference on Computer Vision (ICCV), IEEE, (2021), 9415–9424. https://doi.org/10.1109/ICCV48922.2021.00930
    [85] A. Aimen, S. Sidheekh, N. C. Krishnan, Task attended meta-learning for few-shot learning, preprint, arXiv: 2106.10642.
    [86] R. Krishnan, P. Rajpurkar, E. J. Topol, Self-supervised learning in medicine and healthcare, Nature Biomedical Engineering., 6 (2022), 1346–1352. https://doi.org/10.1038/s41551-022-00914-1 doi: 10.1038/s41551-022-00914-1
    [87] S. Gidaris, P. Singh, N. Komodakis, Unsupervised representation learning by predicting image rotations, preprint, arXiv: 1803.07728.
    [88] W. X. Wang, J. Li, H. Ji, Self-supervised deep image restoration via adaptive stochastic gradient langevin dynamics, in 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, (2022), 1979–1988. https://doi.org/10.1109/CVPR52688.2022.00203
    [89] H. Q. Wang, X. Guo, Z. H. Deng, Y. Lu, Rethinking minimal sufficient representation in contrastive learning, in 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, (2022), 16020-16029. https://doi.org/10.1109/CVPR52688.2022.01557
    [90] M. L. Zhang, J. H. Zhang, Z. W. Lu, T. Xiang, M. Y. Ding, S. F. Huang, IEPT: Instance-Level and Episode-Level Pretext Tasks for Few-Shot Learning, in 2021 International Conference on Learning Representations (ICLR), (2021)
    [91] X. Luo, Y. X. Chen, L. J. Wen, L. L. Pan, Z. L. Xu, Boosting few-shot classification with view-learnable contrastive learning, in 2021 IEEE International Conference on Multimedia and Expo (ICME), IEEE, (2021), 1–6. https://doi.org/10.1109/ICME51207.2021.9428444
    [92] T. Lee, S. Yoo, Augmenting few-shot learning with supervised contrastive learning, IEEE Access., 9 (2021), 61466-61474. https://doi.org/10.1109/ACCESS.2021.3074525 doi: 10.1109/ACCESS.2021.3074525
    [93] Z. Y. Yang, J. H. Wang, Y. Y. Zhu, Few-shot classification with contrastive learning, in 2022 European conference computer vision (ECCV), (2022), 293–309. https://doi.org/10.1007/978-3-031-20044-1_17
    [94] Y. N. Lu, L. J. Wen, J. Z. Liu, Self-supervision can be a good few-shot learner, in 2022 European conference computer vision (ECCV), (2022), 740–758. https://doi.org/10.1007/978-3-031-19800-7_43
    [95] S. Fort, Gaussian prototypical networks for few-shot learning on omniglot, preprint, arXiv: 1708.02735.
    [96] L. Bertinetto, J. F. Henriques, P. H.S. Torr, A. Vedaldi, Meta-learning with differentiable closed-form solvers, preprint, arXiv: 1805.08136.
    [97] C. Wah, S. Branson, P. Welinder, P. Perona, S. Belongie, The caltech-ucsd birds-200-2011 dataset: Technical report CNS-TR-2011-001, (2011), 1–8.
    [98] A. Khosla, N. Jayadevaprakash, B. P. Yao, F. F. Li, Novel dataset for fine-grained image categorization: stanford dogs, CVPR Workshop on Fine-Grained Visual Categorization., 2 (2021).
    [99] M. Y. Ren, E. Triantafillou, S. Ravi, J. Snell, K. Swersky, J. B. Tenenbaum, et al., Meta-learning for semi-supervised few-shot classification, preprint, arXiv: 1803.00676.
    [100] G. Liu, L. L. Zhao, W. Li, D. S. Guo, X. Z. Fang, Class-wise Metric Scaling for Improved Few-Shot Classification, in 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, (2021), 586–595. https://doi.org/10.1109/WACV48630.2021.00063
  • This article has been cited by:

    1. Xinling Li, Xueli Qin, Zhiwei Wan, Weipeng Tai, Chaos synchronization of stochastic time-delay Lur'e systems: An asynchronous and adaptive event-triggered control approach, 2023, 31, 2688-1594, 5589, 10.3934/era.2023284
    2. Jingya Wang, Ye Zhu, L2L control for memristive NNs with non-necessarily differentiable time-varying delay, 2023, 20, 1551-0018, 13182, 10.3934/mbe.2023588
  • Reader Comments
  • © 2024 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0)
通讯作者: 陈斌, bchen63@163.com
  • 1. 

    沈阳化工大学材料科学与工程学院 沈阳 110142

  1. 本站搜索
  2. 百度学术搜索
  3. 万方数据库搜索
  4. CNKI搜索

Metrics

Article views(4577) PDF downloads(1011) Cited by(13)

Figures and Tables

Figures(13)  /  Tables(3)

Other Articles By Authors

/

DownLoad:  Full-Size Img  PowerPoint
Return
Return

Catalog