Contrastive Learning Via Equivariant Representation
Invariant Contrastive Learning (ICL) methods have achieved impressive performance across various domains. However, the absence of latent space representation for distortion (augmentation)-related information in the latent space makes ICL sub-optimal regarding training efficiency and robustness in downstream tasks. Recent studies suggest that introducing equivariance into Contrastive Learning (CL) can improve overall performance. In this paper, we revisit the roles of augmentation strategies and equivariance in improving CL's efficacy. We propose CLeVER (Contrastive Learning Via Equivariant Representation), a novel equivariant contrastive learning framework compatible with augmentation strategies of arbitrary complexity for various mainstream CL backbone models. Experimental results demonstrate that CLeVER effectively extracts and incorporates equivariant information from practical natural images, thereby improving the training efficiency and robustness of baseline models in downstream tasks and achieving state-of-the-art (SOTA) performance. Moreover, we find that leveraging equivariant information extracted by CLeVER simultaneously enhances rotational invariance and sensitivity across experimental tasks, and helps stabilize the framework when handling complex augmentations, particularly for models with small-scale backbones.
Code (0)
등록된 구현이 없습니다.
Tasks
Contrastive LearningMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
ESCL: Equivariant Self-Contrastive Learning for Sentence Representations
Previous contrastive learning methods for sentence representations often focus on insensitive transformations to produce positive pairs, but neglect the role of sensitive transformations that are harmful to semantic repr…
Contrastive LearningMulti-Task LearningSemantic Textual SimilaritySentenceCIPER: Combining Invariant and Equivariant Representations Using Contrastive and Predictive Learning
Self-supervised representation learning (SSRL) methods have shown great success in computer vision. In recent studies, augmentation-based contrastive learning methods have been proposed for learning representations that …
Contrastive LearningData AugmentationRepresentation LearningPeCLR: Self-Supervised 3D Hand Pose Estimation from monocular RGB via Equivariant Contrastive Learning
Encouraged by the success of contrastive learning on image classification tasks, we propose a new self-supervised method for the structured regression task of 3D hand pose estimation. Contrastive learning makes use of un…
3D Hand Pose EstimationContrastive LearningHand Pose Estimationimage-classification+4Learning Temporally Equivariance for Degenerative Disease Progression in OCT by Predicting Future Representations
Contrastive pretraining provides robust representations by ensuring their invariance to different image transformations while simultaneously preventing representational collapse. Equivariant contrastive learning, on the …
Contrastive LearningEquivariant Goal Conditioned Contrastive Reinforcement Learning
Contrastive Reinforcement Learning (CRL) provides a promising framework for extracting useful structured representations from unlabeled interactions. By pulling together state-action pairs and their corresponding future …
Reinforcement LearningOffline RL