# ContrastMask: Contrastive Learning to Segment Every Thing

arXiv: https://arxiv.org/abs/2203.09775 · HTML: https://mlsanity.com/paper/2203.09775/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- Builds on 41 of its 46 references that are in the map.
- First posted on arXiv 18 Mar 2022.

## Builds on (most cited first, 30 of 41)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [Aggregated Residual Transformations for Deep Neural Networks](https://mlsanity.com/paper/1611.05431/) (2016)
- [Learning Deep Features for Discriminative Localization](https://mlsanity.com/paper/1512.04150/) (2015)
- [FCOS: Fully Convolutional One-Stage Object Detection](https://mlsanity.com/paper/1904.01355/) (2019)
- [Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hypersphere](https://mlsanity.com/paper/2005.10242/) (2020)
- [MMDetection: Open MMLab Detection Toolbox and Benchmark](https://mlsanity.com/paper/1906.07155/) (2019)
- [Stacked Hourglass Networks for Human Pose Estimation](https://mlsanity.com/paper/1603.06937/) (2016)
- [Path Aggregation Network for Instance Segmentation](https://mlsanity.com/paper/1803.01534/) (2018)
- [Dense Contrastive Learning for Self-Supervised Visual Pre-Training](https://mlsanity.com/paper/2011.09157/) (2020)
- [Hybrid Task Cascade for Instance Segmentation](https://mlsanity.com/paper/1901.07518/) (2019)
- [YOLACT: Real-time Instance Segmentation](https://mlsanity.com/paper/1904.02689/) (2019)
- [Understanding the Behaviour of Contrastive Loss](https://mlsanity.com/paper/2012.09740/) (2020)
- [Conditional Convolutions for Instance Segmentation](https://mlsanity.com/paper/2003.05664/) (2020)
- [Contrastive learning of global and local features for medical image segmentation with limited annotations](https://mlsanity.com/paper/2006.10511/) (2020)
- [Propagate Yourself: Exploring Pixel-Level Consistency for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/2011.10043/) (2020)
- [NAS-FPN: Learning Scalable Feature Pyramid Architecture for Object Detection](https://mlsanity.com/paper/1904.07392/) (2019)
- [SOLO: Segmenting Objects by Locations](https://mlsanity.com/paper/1912.04488/) (2019)
- [Mask Scoring R-CNN](https://mlsanity.com/paper/1903.00241/) (2019)
- [BoxSup: Exploiting Bounding Boxes to Supervise Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1503.01640/) (2015)
- [Simple Does It: Weakly Supervised Instance and Semantic Segmentation](https://mlsanity.com/paper/1603.07485/) (2016)
- [DetCo: Unsupervised Contrastive Learning for Object Detection](https://mlsanity.com/paper/2102.04803/) (2021)
- [PolarMask: Single Shot Instance Segmentation with Polar Representation](https://mlsanity.com/paper/1909.13226/) (2019)
- [Unsupervised Learning of Dense Visual Representations](https://mlsanity.com/paper/2011.05499/) (2020)
- [BlendMask: Top-Down Meets Bottom-Up for Instance Segmentation](https://mlsanity.com/paper/2001.00309/) (2020)
- [Semi-Supervised Semantic Segmentation with Pixel-Level Contrastive Learning from a Class-wise Memory Bank](https://mlsanity.com/paper/2104.13415/) (2021)

## Built on by (most cited first, 20 of 20)

- [Bidirectional Copy-Paste for Semi-Supervised Medical Image Segmentation](https://mlsanity.com/paper/2305.00673/) (2023)
- [A Survey on Label-efficient Deep Image Segmentation: Bridging the Gap between Weak Supervision and Dense Prediction](https://mlsanity.com/paper/2207.01223/) (2022)
- [H2RBox: Horizontal Box Annotation is All You Need for Oriented Object Detection](https://mlsanity.com/paper/2210.06742/) (2022)
- [DeNVeR: Deformable Neural Vessel Representations for Unsupervised Video Vessel Segmentation](https://mlsanity.com/paper/2406.01591/) (2024)
- [Deblurring Masked Autoencoder is Better Recipe for Ultrasound Image Recognition](https://mlsanity.com/paper/2306.08249/) (2023)
- [Learning Referring Video Object Segmentation from Weak Annotation](https://mlsanity.com/paper/2308.02162/) (2023)
- [COMICS: End-to-end Bi-grained Contrastive Learning for Multi-face Forgery Detection](https://mlsanity.com/paper/2308.01520/) (2023)
- [Aerial Image Object Detection With Vision Transformer Detector (ViTDet)](https://mlsanity.com/paper/2301.12058/) (2023)
- [Remote Sensing Scene Classification with Masked Image Modeling (MIM)](https://mlsanity.com/paper/2302.14256/) (2023)
- [FreeCOS: Self-Supervised Learning from Fractals and Unlabeled Images for Curvilinear Object Segmentation](https://mlsanity.com/paper/2307.07245/) (2023)
- [Seamless Detection: Unifying Salient Object Detection and Camouflaged Object Detection](https://mlsanity.com/paper/2412.16840/) (2024)
- [Synchronizing Vision and Language: Bidirectional Token-Masking AutoEncoder for Referring Image Segmentation](https://mlsanity.com/paper/2311.17952/) (2023)
- [Beyond Traditional Single Object Tracking: A Survey](https://mlsanity.com/paper/2405.10439/) (2024)
- [Weakly Supervised Segmentation Framework for Thyroid Nodule Based on High-confidence Labels and High-rationality Losses](https://mlsanity.com/paper/2502.19707/) (2025)
- [Grounding Bodily Awareness in Visual Representations for Efficient Policy Learning](https://mlsanity.com/paper/2505.18487/) (2025)
- [CAST: Contrastive Adaptation and Distillation for Semi-Supervised Instance Segmentation](https://mlsanity.com/paper/2505.21904/) (2025)
- [Ensemble Foreground Management for Unsupervised Object Discovery](https://mlsanity.com/paper/2507.20860/) (2025)
- [Training a Student Expert via Semi-Supervised Foundation Model Distillation](https://mlsanity.com/paper/2604.03841/) (2026)
- [WaveDINO: Learning-Based Atmospheric Correction of Unwrapped InSAR Interferograms Validated by GNSS: Results at Laguna del Maule and Campi Flegrei Volcanoes](https://mlsanity.com/paper/2606.16795/) (2026)
- [A Concept-informed Interpretable Artificial Intelligence Framework for Breast Ultrasound Diagnosis](https://mlsanity.com/paper/2610.16128/) (2026)

## Abstract (arXiv)

Partially-supervised instance segmentation is a task which requests segmenting objects from novel unseen categories via learning on limited seen categories with annotated masks thus eliminating demands of heavy annotation burden. The key to addressing this task is to build an effective class-agnostic mask segmentation model. Unlike previous methods that learn such models only on seen categories, in this paper, we propose a new method, named ContrastMask, which learns a mask segmentation model on both seen and unseen categories under a unified pixel-level contrastive learning framework. In this framework, annotated masks of seen categories and pseudo masks of unseen categories serve as a prior for contrastive learning, where features from the mask regions (foreground) are pulled together, and are contrasted against those from the background, and vice versa. Through this framework, feature discrimination between foreground and background is largely improved, facilitating learning of the class-agnostic mask segmentation model. Exhaustive experiments on the COCO dataset demonstrate the superiority of our method, which outperforms previous state-of-the-arts.