CO2: Consistent Contrast for Unsupervised Visual Representation Learning

by   Chen Wei, et al.

Contrastive learning has been adopted as a core method for unsupervised visual representation learning. Without human annotation, the common practice is to perform an instance discrimination task: Given a query image crop, this task labels crops from the same image as positives, and crops from other randomly sampled images as negatives. An important limitation of this label assignment strategy is that it can not reflect the heterogeneous similarity between the query crop and each crop from other images, taking them as equally negative, while some of them may even belong to the same semantic class as the query. To address this issue, inspired by consistency regularization in semi-supervised learning on unlabeled data, we propose Consistent Contrast (CO2), which introduces a consistency regularization term into the current contrastive learning framework. Regarding the similarity of the query crop to each crop from other images as "unlabeled", the consistency term takes the corresponding similarity of a positive crop as a pseudo label, and encourages consistency between these two similarities. Empirically, CO2 improves Momentum Contrast (MoCo) by 2.9 1.1 transfers to image classification, object detection, and semantic segmentation on PASCAL VOC. This shows that CO2 learns better visual representations for these downstream tasks.


page 1

page 2

page 3

page 4


UniMoCo: Unsupervised, Semi-Supervised and Full-Supervised Visual Representation Learning

Momentum Contrast (MoCo) achieves great success for unsupervised visual ...

A Theory-Driven Self-Labeling Refinement Method for Contrastive Representation Learning

For an image query, unsupervised contrastive learning labels crops of th...

CORE: Consistent Representation Learning for Face Forgery Detection

Face manipulation techniques develop rapidly and arouse widespread publi...

Towards Effective Visual Representations for Partial-Label Learning

Under partial-label learning (PLL) where, for each training instance, on...

Iterative Reorganization with Weak Spatial Constraints: Solving Arbitrary Jigsaw Puzzles for Unsupervised Representation Learning

Learning visual features from unlabeled image data is an important yet c...

SUVR: A Search-based Approach to Unsupervised Visual Representation Learning

Unsupervised learning has grown in popularity because of the difficulty ...

Deep Semi-supervised Learning with Double-Contrast of Features and Semantics

In recent years, the field of intelligent transportation systems (ITS) h...

Please sign up or login with your details

Forgot password? Click here to reset