Negative Margin Matters: Understanding Margin in Few-Shot Classification

Liu, Bin; Cao, Yue; Lin, Yutong; Li, Qi; Zhang, Zheng; Long, Mingsheng; Hu, Han

doi:10.1007/978-3-030-58548-8_26

Cited by 244 publications

(114 citation statements)

References 22 publications

Supporting

Mentioning

110

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

“…Manifold mixup [12] shows that the pre-training and fine-tuning pipeline can achieve competitive performance with few-shot classification. Negative Matters [4] help discriminate against fiction classes by avoiding wrong mapping samples of the same novel class to multiple tasks. MML [5] calculates the multi-level similarity to capture more information.…”

Section: Meta-learning Based Few-shot Learning Methodsmentioning

confidence: 99%

Distribution Estimation Based Pseudo-Feature Library Generation For Few-Shot Image Classification

Zhang

Liu

Zhao

et al. 2021

2021 IEEE International Conference on Multimedia &Amp; Expo Workshops (ICMEW)

View full text Add to dashboard Cite

Due to the high cost of labeled data acquisition, few-shot learning has attracted great attention in recent years. The biased estimation of class distribution from a few labeled samples hinders the model's performance. Some existing methods generate samples or features by a learning module or network. In this paper, a distribution-based pseudo-feature library generation method is proposed, and it follows a simple distribution modeling hypothesis. The base class features is introduced to better estimate the novel class distribution. Furthermore, a patch-level pseudo-feature library is adversarially generated to reinforce the training of the classifier. The proposed method significantly improves the model performance for the few-shot image classification task without introducing additional training parameters. Our method ranks first in the ICME 2021 Few-Shot Learning for Vehicle Footprint Recognition Challenge, demonstrating its effectiveness.

show abstract

“…As pointed by [12,19,20], the major challenge in few-shot learning is to learn more discriminative and transferable image features for novel classes. However, these prevailing methods are still sensitive to background clutter, especially when the number of training samples per category is limited.…”

Section: Sgca For Generalizable Representation Learningmentioning

confidence: 99%

Saliency-Guided Complementary Attention for Improved Few-Shot Learning

Zhao

Liu

Guo

et al. 2021

2021 IEEE International Conference on Multimedia and Expo (ICME)

View full text Add to dashboard Cite

Despite significant progress in recent deep neural networks, most deep learning algorithms rely heavily on abundant training samples. To address this problem, we propose an effective and interpretable few-shot classification model using Saliency-Guided Complementary Attention (SGCA), which aims to learn transferable representations and to build a robust classification module simultaneously. Concretely, we propose to train our feature extractor using an auxiliary task to separate object regions from background clutter guided by saliency detection signals. In addition, to make the separation beneficial to the downstream tasks, we introduce a complementary attention mechanism to force the classification module to focus on various informative parts of the image. Extensive experiments on few-shot learning tasks demonstrate the effectiveness of our proposed method, e.g., we achieve 68.81% and 84.60% for 5-way 1-shot and 5-shot settings on mini-ImageNet, respectively.

show abstract

Negative Margin Matters: Understanding Margin in Few-Shot Classification

Cited by 244 publications

References 22 publications

Feature Transformation Network for Few-Shot Learning

Feature Transformation Network for Few-Shot Learning

Distribution Estimation Based Pseudo-Feature Library Generation For Few-Shot Image Classification

Saliency-Guided Complementary Attention for Improved Few-Shot Learning

Contact Info

Product

Resources

About