# CO2: Consistent Contrast for Unsupervised Visual Representation Learning

arXiv: https://arxiv.org/abs/2010.02217 · HTML: https://mlsanity.com/paper/2010.02217/

## Key facts

- Cited by 38 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Oct 2020.

## Built on by (most cited first, 30 of 38)

- [Contrastive Learning with Stronger Augmentations](https://mlsanity.com/paper/2104.07713/) (2021)
- [ICE: Inter-instance Contrastive Encoding for Unsupervised Person Re-identification](https://mlsanity.com/paper/2103.16364/) (2021)
- [Mean Shift for Self-Supervised Learning](https://mlsanity.com/paper/2105.07269/) (2021)
- [Soft Contrastive Learning for Time Series](https://mlsanity.com/paper/2312.16424/) (2023)
- [Contrastive Learning with Continuous Proxy Meta-Data for 3D MRI Classification](https://mlsanity.com/paper/2106.08808/) (2021)
- [Improving Contrastive Learning by Visualizing Feature Transformation](https://mlsanity.com/paper/2108.02982/) (2021)
- [Exploring Patch-wise Semantic Relation for Contrastive Learning in Image-to-Image Translation Tasks](https://mlsanity.com/paper/2203.01532/) (2022)
- [Hierarchical Consistent Contrastive Learning for Skeleton-Based Action Recognition with Growing Augmentations](https://mlsanity.com/paper/2211.13466/) (2022)
- [Enhancing Self-supervised Video Representation Learning via Multi-level Feature Optimization](https://mlsanity.com/paper/2108.02183/) (2021)
- [CP2: Copy-Paste Contrastive Pretraining for Semantic Segmentation](https://mlsanity.com/paper/2203.11709/) (2022)
- [Prompted Contrast with Masked Motion Modeling: Towards Versatile 3D Action Representation Learning](https://mlsanity.com/paper/2308.03975/) (2023)
- [APoLLo: Unified Adapter and Prompt Learning for Vision Language Models](https://mlsanity.com/paper/2312.01564/) (2023)
- [Similarity Contrastive Estimation for Self-Supervised Soft Contrastive Learning](https://mlsanity.com/paper/2111.14585/) (2021)
- [Adaptive Soft Contrastive Learning](https://mlsanity.com/paper/2207.11163/) (2022)
- [Temporal Knowledge Consistency for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/2108.10668/) (2021)
- [A Theory-Driven Self-Labeling Refinement Method for Contrastive Representation Learning](https://mlsanity.com/paper/2106.14749/) (2021)
- [Constrained Mean Shift Using Distant Yet Related Neighbors for Representation Learning](https://mlsanity.com/paper/2112.04607/) (2021)
- [Relational Contrastive Learning for Scene Text Recognition](https://mlsanity.com/paper/2308.00508/) (2023)
- [Separating common from salient patterns with Contrastive Representation Learning](https://mlsanity.com/paper/2402.11928/) (2024)
- [MixSiam: A Mixture-based Approach to Self-supervised Representation Learning](https://mlsanity.com/paper/2111.02679/) (2021)
- [Beyond Instance Discrimination: Relation-aware Contrastive Self-supervised Learning](https://mlsanity.com/paper/2211.01796/) (2022)
- [Generalized Category Discovery with Clustering Assignment Consistency](https://mlsanity.com/paper/2310.19210/) (2023)
- [CoUn: Empowering Machine Unlearning via Contrastive Learning](https://mlsanity.com/paper/2509.16391/) (2025)
- [Self-Supervised Learning for Text Recognition: A Critical Survey](https://mlsanity.com/paper/2407.19889/) (2024)
- [Similarity Contrastive Estimation for Image and Video Soft Contrastive Self-Supervised Learning](https://mlsanity.com/paper/2212.11187/) (2022)
- [Unsupervised Synthetic Image Refinement via Contrastive Learning and Consistent Semantic-Structural Constraints](https://mlsanity.com/paper/2304.12591/) (2023)
- [USL-Net: Uncertainty Self-Learning Network for Unsupervised Skin Lesion Segmentation](https://mlsanity.com/paper/2309.13289/) (2023)
- [Exploring the Diversity and Invariance in Yourself for Visual Pre-Training Task](https://mlsanity.com/paper/2106.00537/) (2021)
- [Unsupervised Representation Learning for Binary Networks by Joint Classifier Learning](https://mlsanity.com/paper/2110.08851/) (2021)
- [Trip-ROMA: Self-Supervised Learning with Triplets and Random Mappings](https://mlsanity.com/paper/2107.10419/) (2021)

## Abstract (arXiv)

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% top-1 accuracy on ImageNet linear protocol, 3.8% and 1.1% top-5 accuracy on 1% and 10% labeled semi-supervised settings. It also transfers to image classification, object detection, and semantic segmentation on PASCAL VOC. This shows that CO2 learns better visual representations for these downstream tasks.