Boosting Few-Shot Learning via Attentive Feature Regularization
Few-shot learning (FSL) based on manifold regularization aims to improve the recognition capacity of novel objects with limited training samples by mixing two samples from different categories with a blending factor. However, this mixing operation weakens the feature representation due to the linear interpolation and the overlooking of the importance of specific channels. To solve these issues, this paper proposes attentive feature regularization (AFR) which aims to improve the feature representativeness and discriminability. In our approach, we first calculate the relations between different categories of semantic labels to pick out the related features used for regularization. Then, we design two attention-based calculations at both the instance and channel levels. These calculations enable the regularization procedure to focus on two crucial aspects: the feature complementarity through adaptive interpolation in related categories and the emphasis on specific feature channels. Finally, we combine these regularization strategies to significantly improve the classifier performance. Empirical studies on several popular FSL benchmarks demonstrate the effectiveness of AFR, which improves the recognition accuracy of novel categories without the need to retrain any feature extractor, especially in the 1-shot setting. Furthermore, the proposed AFR can seamlessly integrate into other FSL methods to improve classification performance.
Code (0)
등록된 구현이 없습니다.
Tasks
Few-Shot LearningMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Boosted Zero-Shot Learning with Semantic Correlation Regularization
We study zero-shot learning (ZSL) as a transfer learning problem, and focus on the two key aspects of ZSL, model effectiveness and model adaptation. For effective modeling, we adopt the boosting strategy to learn a zero-…
Model SelectionTransfer Learningzero-shot-classificationZero-Shot LearningDeMFI: Deep Joint Deblurring and Multi-Frame Interpolation with Flow-Guided Attentive Correlation and Recursive Boosting
In this paper, we propose a novel joint deblurring and multi-frame interpolation (DeMFI) framework, called DeMFI-Net, which accurately converts blurry videos of lower-frame-rate to sharp videos at higher-frame-rate based…
DeblurringVideo EnhancementVideo Frame InterpolationVideo RestorationThe Theory Behind Overfitting, Cross Validation, Regularization, Bagging, and Boosting: Tutorial
In this tutorial paper, we first define mean squared error, variance, covariance, and bias of both random variables and classification/predictor models. Then, we formulate the true and generalization errors of the model …
L2 RegularizationVision Transformer with Attentive Pooling for Robust Facial Expression Recognition
Facial Expression Recognition (FER) in the wild is an extremely challenging task. Recently, some Vision Transformers (ViT) have been explored for FER, but most of them perform inferiorly compared to Convolutional Neural …
Facial Expression RecognitionFacial Expression Recognition (FER)Inductive BiasAttentive Prototype Few-shot Learning with Capsule Network-based Embedding
Few-shot learning, namely recognizing novel categories with a very small amount of training examples, is a challenging area of machine learning research. Traditional deep learning methods require massive training data to…
ClassificationFew-Shot LearningGeneral ClassificationTriplet