An Ensemble of Epoch-Wise Empirical Bayes for Few-Shot Learning

Liu, Yaoyao; Schiele, Bernt; Sun, Quansen

doi:10.1007/978-3-030-58517-4_24

Cited by 90 publications

(44 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…• Extensive experiments on two popular standard fewshot classification benchmark datasets-general object dataset mini-ImageNet and fine-grained dataset Caltech-UCSD Birds-200-2011 (CUB), show that the proposed method surpasses some state-of-the-art methods [17]- [21], [28], [34], [37], [44], and validate the feasibility of our model.…”

Section: Introductionmentioning

confidence: 61%

“…We implement experiments on mini-ImageNet and CUB datasets, and compare our model with a series of current prevailing models, including Matching Networks [10], MAML [13], Prototypical Networks [17], Relation Networks [18], TADAM [19], MetaOptNet [37], Baseline++ [20], Meta-Baseline [21], DSN [34], E 3 BM [44], Neg-Cosine [28]. The experimental results are listed in Table 2 and Table 3, respectively.…”

Section: Comparison With the State-of-the-artsmentioning

confidence: 99%

See 1 more Smart Citation

Feature Transformation Network for Few-Shot Learning

Wang

Zhou

2021

IEEE Access

View full text Add to dashboard Cite

Few-shot learning researches to learn a novel concept from a handful of labeled samples. Due to the small amount of training data, deep network has the risk of over-fitting. Although many previous approaches based on metric criterion can make significant progress to tackle this challenge, they not only ignore the association between query set and support set when learning sample representation, but also fail to focus greater attention in the target area. To cope with these issues, we propose a novel feature transformation network (FTN) for few-shot image classification. Specifically, to draw inferences about other instances from only a few examples, it is expected to learn a model that has more discriminative representation of the target attributes and robust generalization ability. To this end, we introduce an attention-based affinity matrix to transform the semantical enhanced embedding vectors of query samples by associating the support set, thereby guiding the network to learn a sample representation that embodies higher semantic information in the target area. Furthermore, aiming at highlighting the object region in the feature maps, and strengthening the pertinence of similarity measurement between samples, a global and local feature fusion module is designed to fuse the support set samples features. The comprehensive experiments validate the doable of our model, and our method achieves the state-of-the-art performance on two public benchmark datasets, namely, general object dataset mini-ImageNet and fine-grained dataset Caltech-UCSD Birds-200-2011 (CUB). INDEX TERMS Few-shot learning, feature transformation, feature fusion, metric criterion.

show abstract

Section: Introductionmentioning

confidence: 61%

Section: Comparison With the State-of-the-artsmentioning

confidence: 99%

Feature Transformation Network for Few-Shot Learning

Wang

Zhou

2021

IEEE Access

View full text Add to dashboard Cite

show abstract

“…">Memory network methods (i.e., Meta Networks, 103 TADAM, 104 MCFS, 105 and MRN 106 ) learn to store “experience” when learning seen tasks and then generalize it to unseen tasks. Gradient descent‐based meta‐learning methods (i.e., MAML, 35 Meta‐LSTM, 107 MetaGAN, 42 LEO, 108 LGM‐Net, 109 CTM, 110 MetaOptNet, 111 SIB + E3BM, 141 and LSBC 112 ) intend for adjusting the optimization algorithm so that the model can converge within a small number of optimization steps (with a few examples).…”

Section: Methodsmentioning

confidence: 99%

“…Gradient descent‐based meta‐learning methods (i.e., MAML, 35 Meta‐LSTM, 107 MetaGAN, 42 LEO, 108 LGM‐Net, 109 CTM, 110 MetaOptNet, 111 SIB + E3BM, 141 and LSBC 112 ) intend for adjusting the optimization algorithm so that the model can converge within a small number of optimization steps (with a few examples).…”

Section: Methodsmentioning

confidence: 99%

Fighting fire with fire: A spatial–frequency ensemble relation network with generative adversarial learning for adversarial image classification

et al. 2021

View full text Add to dashboard Cite

Adversarial images generated by generative adversarial networks are not close to any existing benign images, and contain nonrobust features that have been identified as critical to the robustness of a machine learning model. Since adversarial images have an underlying distribution that differs from normal images, these kinds of images can offer valuable features for training a robust model. To deal with these special features, we focus on a novel machine learning task of adversarial images classification, where adversarial images can be used to investigate the problem of classifying adversarial images themselves. In the setting of this novel task, adversarial images are the ONLY kind of data used in training and testing, rather than not just a set of testing images as usual. To this end, we propose a novel spatial–frequency ensemble relation network with generative adversarial learning. First, we present a spatial–frequency ensemble representation learning to extract the feature of training images. Second, we design a meta‐learning‐based relation model to gain the relationship between images. Third, to achieve a robust model, we utilize generative adversarial learning and transform the relationship into a Jacobian matrix. Finally, we design a discriminator model that determines whether an adversarial image is from the matching category or not. Experimental results demonstrate that our approach achieves significantly higher performance compared with other state‐of‐the‐arts.

show abstract

“…Few-shot learning aims to learn to generalize to new categories with a few labeled samples in each class. Current few-shot methods mainly include optimization-based methods [12,23,32,39,45,46,55] and metric-based methods [13,19,44,49,52,58,57,53]. Optimization-based methods can achieve fast adaptation to new tasks with limited samples by learning a specific optimization algorithm.…”

Section: Related Workmentioning

confidence: 99%

Overcoming Catastrophic Forgetting in Incremental Few-Shot Learning by Finding Flat Minima

Shi¹,

Chen²,

Zhang³

et al. 2021

Preprint

View full text Add to dashboard Cite

This paper considers incremental few-shot learning, which requires a model to continually recognize new categories with only a few examples provided. Our study shows that existing methods severely suffer from catastrophic forgetting, a well-known problem in incremental learning, which is aggravated due to data scarcity and imbalance in the few-shot setting. Our analysis further suggests that to prevent catastrophic forgetting, actions need to be taken in the primitive stagethe training of base classes instead of later few-shot learning sessions. Therefore, we propose to search for flat local minima of the base training objective function and then fine-tune the model parameters within the flat region on new tasks. In this way, the model can efficiently learn new classes while preserving the old ones. Comprehensive experimental results demonstrate that our approach outperforms all prior state-of-the-art methods and is very close to the approximate upper bound. The source code is available at https://github.com/moukamisama/F2M.

show abstract

An Ensemble of Epoch-Wise Empirical Bayes for Few-Shot Learning

Cited by 90 publications

References 30 publications

Feature Transformation Network for Few-Shot Learning

Feature Transformation Network for Few-Shot Learning

Fighting fire with fire: A spatial–frequency ensemble relation network with generative adversarial learning for adversarial image classification

Overcoming Catastrophic Forgetting in Incremental Few-Shot Learning by Finding Flat Minima

Contact Info

Product

Resources

About