Unsupervised Embedding Adaptation via Early-Stage Feature Reconstruction for Few-Shot Classification
We propose unsupervised embedding adaptation for the downstream few-shot classification task. Based on findings that deep neural networks learn to generalize before memorizing, we develop Early-Stage Feature Reconstruction (ESFR) -- a novel adaptation scheme with feature reconstruction and dimensionality-driven early stopping that finds generalizable features. Incorporating ESFR consistently improves the performance of baseline methods on all standard settings, including the recently proposed transductive method. ESFR used in conjunction with the transductive method further achieves state-of-the-art performance on mini-ImageNet, tiered-ImageNet, and CUB; especially with 1.2%~2.0% improvements in accuracy over the previous best performing method on 1-shot setting.
Code (1)
Tasks
Few-Shot Image ClassificationFew-Shot LearningMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Part-of-Speech Tagging for Historical English
As more historical texts are digitized, there is interest in applying natural language processing tools to these archives. However, the performance of these tools is often unsatisfactory, due to language change and genre…
Domain AdaptationPart-Of-Speech TaggingUnsupervised Domain AdaptationWord EmbeddingsUnsupervised Domain Adaptation with Feature Embeddings
Representation learning is the dominant technique for unsupervised domain adaptation, but existing approaches often require the specification of "pivot features" that generalize across domains, which are selected by task…
Domain AdaptationRepresentation LearningUnsupervised Domain AdaptationPseudo-Labeling Curriculum for Unsupervised Domain Adaptation
To learn target discriminative representations, using pseudo-labels is a simple yet effective approach for unsupervised domain adaptation. However, the existence of false pseudo-labels, which may have a detrimental influ…
ClusteringDomain AdaptationSemi-Supervised Image ClassificationUnsupervised Domain AdaptationSelf-supervised Feature Adaptation for 3D Industrial Anomaly Detection
Industrial anomaly detection is generally addressed as an unsupervised task that aims at locating defects with only normal training samples. Recently, numerous 2D anomaly detection methods have been proposed and have ach…
Anomaly Detectioncross-modal alignmentPrototypical 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+1