Revisiting Prototypical Network for Cross Domain Few-Shot Learning
Prototypical Network is a popular few-shot solver that aims at establishing a feature metric generalizable to novel few-shot classification (FSC) tasks using deep neural networks. However, its performance drops dramatically when generalizing to the FSC tasks in new domains. In this study, we revisit this problem and argue that the devil lies in the simplicity bias pitfall in neural networks. In specific, the network tends to focus on some biased shortcut features (e.g., color, shape, etc.) that are exclusively sufficient to distinguish very few classes in the meta-training tasks within a pre-defined domain, but fail to generalize across domains as some desirable semantic features. To mitigate this problem, we propose a Local-global Distillation Prototypical Network (LDP-net). Different from the standard Prototypical Network, we establish a two-branch network to classify the query image and its random local crops, respectively. Then, knowledge distillation is conducted among these two branches to enforce their class affiliation consistency. The rationale behind is that since such global-local semantic relationship is expected to hold regardless of data domains, the local-global distillation is beneficial to exploit some cross-domain transferable semantic features for feature metric establishment. Moreover, such local-global semantic consistency is further enforced among different images of the same class to reduce the intra-class semantic variation of the resultant feature. In addition, we propose to update the local branch as Exponential Moving Average (EMA) over training episodes, which makes it possible to better distill cross-episode knowledge and further enhance the generalization performance. Experiments on eight cross-domain FSC benchmarks empirically clarify our argument and show the state-of-the-art results of LDP-net. Code is available in https://github.com/NWPUZhoufei/LDP-Net
Code (1)
Tasks
Cross-Domain Few-Shotcross-domain few-shot learningFew-Shot LearningKnowledge DistillationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Prototypical Cross-domain Self-supervised Learning for Few-shot Unsupervised Domain Adaptation
Unsupervised Domain Adaptation (UDA) transfers predictive models from a fully-labeled source domain to an unlabeled target domain. In some applications, however, it is expensive even to collect labels in the source domai…
Contrastive LearningDomain AdaptationSelf-Supervised LearningSemantic Segmentation+1Bridge to Target Domain by Prototypical Contrastive Learning and Label Confusion: Re-explore Zero-Shot Learning for Slot Filling
Zero-shot cross-domain slot filling alleviates the data dependence in the case of data scarcity in the target domain, which has aroused extensive research. However, as most of the existing methods do not achieve effectiv…
Contrastive Learningslot-fillingSlot FillingTransfer Learning+2Doodle Your Keypoints: Sketch-Based Few-Shot Keypoint Detection
Keypoint detection, integral to modern machine perception, faces challenges in few-shot learning, particularly when source data from the same distribution as the query is unavailable. This gap is addressed by leveraging …
Domain AdaptationFew-Shot LearningKeypoint DetectionSemi-supervised Meta-learning for Cross-domain Few-shot Intent Classification
Meta learning aims to optimize the model’s capability to generalize to new tasks and domains. Lacking a data-efficient way to create meta training tasks has prevented the application of meta-learning to the real-world fe…
Cross-Domain Few-ShotFew-Shot Learningintent-classificationIntent Classification+3Self-Supervised Prototypical Transfer Learning for Few-Shot Classification
Most approaches in few-shot learning rely on costly annotated data related to the goal task domain during (pre-)training. Recently, unsupervised meta-learning methods have exchanged the annotation requirement for a reduc…
ClassificationFew-Shot LearningGeneral ClassificationMeta-Learning+4