Adaptive Part Learning for Fine-Grained Generalized Category Discovery: A Plug-and-Play Enhancement
Generalized Category Discovery (GCD) aims to recognize unlabeled images from known and novel classes by distinguishing novel classes from known ones, while also transferring knowledge from another set of labeled images with known classes. Existing GCD methods rely on self-supervised vision transformers such as DINO for representation learning. However, focusing solely on the global representation of the DINO CLS token introduces an inherent trade-off between discriminability and generalization. In this paper, we introduce an adaptive part discovery and learning method, called APL, which generates consistent object parts and their correspondences across different similar images using a set of shared learnable part queries and DINO part priors, without requiring any additional annotations. More importantly, we propose a novel all-min contrastive loss to learn discriminative yet generalizable part representation, which adaptively highlights discriminative object parts to distinguish similar categories for enhanced discriminability while simultaneously sharing other parts to facilitate knowledge transfer for improved generalization. Our APL can easily be incorporated into different GCD frameworks by replacing their CLS token feature with our part representations, showing significant enhancements on fine-grained datasets.
Code (0)
등록된 구현이 없습니다.
Tasks
Representation LearningTransfer LearningMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Adaptive Part Learning for Fine-Grained Generalized Category Discovery: A Plug-and-Play Enhancement
Generalized Category Discovery (GCD) aims to recognize unlabeled images from known and novel classes by distinguishing novel classes from known ones, while also transferring knowledge from another set of labeled images w…
Representation LearningComponent Adaptive Clustering for Generalized Category Discovery
Generalized Category Discovery (GCD) tackles the challenging problem of categorizing unlabeled images into both known and novel classes within a partially labeled dataset, without prior knowledge of the number of unknown…
Contrastive LearningGeneralized Fine-Grained Category Discovery with Multi-Granularity Conceptual Experts
Generalized Category Discovery (GCD) is an open-world problem that clusters unlabeled data by leveraging knowledge from partially labeled categories. A key challenge is that unlabeled data may contain both known and nove…
Fine-Grained Visual RecognitionRepresentation LearningContrastive LearningXCon: Learning with Experts for Fine-grained Category Discovery
We address the problem of generalized category discovery (GCD) in this paper, i.e. clustering the unlabeled images leveraging the information from a set of seen classes, where the unlabeled images could contain both seen…
ClusteringContrastive LearningNovel ConceptsSelEx: Self-Expertise in Fine-Grained Generalized Category Discovery
In this paper, we address Generalized Category Discovery, aiming to simultaneously uncover novel categories and accurately classify known ones. Traditional methods, which lean heavily on self-supervision and contrastive …
Contrastive Learning