Adversarial Feature Augmentation for Cross-domain Few-shot Classification
Existing methods based on meta-learning predict novel-class labels for (target domain) testing tasks via meta knowledge learned from (source domain) training tasks of base classes. However, most existing works may fail to generalize to novel classes due to the probably large domain discrepancy across domains. To address this issue, we propose a novel adversarial feature augmentation (AFA) method to bridge the domain gap in few-shot learning. The feature augmentation is designed to simulate distribution variations by maximizing the domain discrepancy. During adversarial training, the domain discriminator is learned by distinguishing the augmented features (unseen domain) from the original ones (seen domain), while the domain discrepancy is minimized to obtain the optimal feature encoder. The proposed method is a plug-and-play module that can be easily integrated into existing few-shot learning methods based on meta-learning. Extensive experiments on nine datasets demonstrate the superiority of our method for cross-domain few-shot classification compared with the state of the art. Code is available at https://github.com/youthhoo/AFA_For_Few_shot_learning
Code (1)
Tasks
ClassificationCross-Domain Few-ShotFew-Shot LearningMeta-LearningMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
On the Mechanisms of Adversarial Data Augmentation for Robust and Adaptive Transfer Learning
Transfer learning across domains with distribution shift remains a fundamental challenge in building robust and adaptable machine learning systems. While adversarial perturbations are traditionally viewed as threats that…
Data AugmentationDomain AdaptationDomain GeneralizationRepresentation Learning+1Cross-Domain Few-Shot Classification via Adversarial Task Augmentation
Few-shot classification aims to recognize unseen classes with few labeled samples from each class. Many meta-learning models for few-shot classification elaborately design various task-shared inductive bias (meta-knowled…
ClassificationCross-Domain Few-ShotDomain GeneralizationGeneral Classification+2AAPL: Adding Attributes to Prompt Learning for Vision-Language Models
Recent advances in large pre-trained vision-language models have demonstrated remarkable performance on zero-shot downstream tasks. Building upon this, recent studies, such as CoOp and CoCoOp, have proposed the use of pr…
Data AugmentationDomain GeneralizationFew-Shot LearningImage Augmentation+2Decoupling Augmentation Bias in Prompt Learning for Vision-Language Models
Recent advances in large-scale vision and language models have led to significant progress in zero-shot learning tasks. Methods such as CoOp and CoCoOp have shown that replacing handcrafted prompts with learnable vectors…
Domain GeneralizationZero-Shot LearningData AugmentationExploiting Style Transfer-based Task Augmentation for Cross-Domain Few-Shot Learning
In cross-domain few-shot learning, the core issue is that the model trained on source domains struggles to generalize to the target domain, especially when the domain shift is large. Motivated by the observation that the…
Cross-Domain Few-Shotcross-domain few-shot learningDiversityDomain Generalization+3