Cross-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-knowledge) to solve such tasks, and achieve impressive performance. However, when there exists the domain shift between the training tasks and the test tasks, the obtained inductive bias fails to generalize across domains, which degrades the performance of the meta-learning models. In this work, we aim to improve the robustness of the inductive bias through task augmentation. Concretely, we consider the worst-case problem around the source task distribution, and propose the adversarial task augmentation method which can generate the inductive bias-adaptive 'challenging' tasks. Our method can be used as a simple plug-and-play module for various meta-learning models, and improve their cross-domain generalization capability. We conduct extensive experiments under the cross-domain setting, using nine few-shot classification datasets: mini-ImageNet, CUB, Cars, Places, Plantae, CropDiseases, EuroSAT, ISIC and ChestX. Experimental results show that our method can effectively improve the few-shot classification performance of the meta-learning models under domain shift, and outperforms the existing works. Our code is available at https://github.com/Haoqing-Wang/CDFSL-ATA.
Code (1)
Tasks
ClassificationCross-Domain Few-ShotDomain GeneralizationGeneral ClassificationInductive BiasMeta-LearningSimilar Papers 제목 키워드 기반
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 t…
ClassificationCross-Domain Few-ShotFew-Shot LearningMeta-LearningLong-term Cross Adversarial Training: A Robust Meta-learning Method for Few-shot Classification Tasks
Meta-learning model can quickly adapt to new tasks using few-shot labeled data. However, despite achieving good generalization on few-shot classification tasks, it is still challenging to improve the adversarial robustne…
Adversarial RobustnessClassificationFew-Shot LearningMeta-LearningAdversarial Style Mining for One-Shot Unsupervised Domain Adaptation
We aim at the problem named One-Shot Unsupervised Domain Adaptation. Unlike traditional Unsupervised Domain Adaptation, it assumes that only one unlabeled target sample can be available when learning to adapt. This setti…
Domain Adaptationdomain classificationOne-shot Unsupervised Domain AdaptationStyle Transfer+1Improving the Generalization of Meta-learning on Unseen Domains via Adversarial Shift
Meta-learning provides a promising way for learning to efficiently learn and achieves great success in many applications. However, most meta-learning literature focuses on dealing with tasks from a same domain, making it…
Cross-Domain Few-ShotDomain GeneralizationMeta-LearningCross Domain Few-Shot Learning via Meta Adversarial Training
Few-shot relation classification (RC) is one of the critical problems in machine learning. Current research merely focuses on the set-ups that both training and testing are from the same domain. However, in practice, thi…
Cross-Domain Few-Shotcross-domain few-shot learningFew-Shot LearningFew-Shot Relation Classification+1