# Bootstrapping Semantic Segmentation with Regional Contrast

arXiv: https://arxiv.org/abs/2104.04465 · HTML: https://mlsanity.com/paper/2104.04465/

## Key facts

- Cited by 80 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 44 references that are in the map.
- First posted on arXiv 9 Apr 2021.

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

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [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)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs](https://mlsanity.com/paper/1606.00915/) (2016)
- [Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1802.02611/) (2018)
- [Supervised Contrastive Learning](https://mlsanity.com/paper/2004.11362/) (2020)
- [FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence](https://mlsanity.com/paper/2001.07685/) (2020)
- [MixMatch: A Holistic Approach to Semi-Supervised Learning](https://mlsanity.com/paper/1905.02249/) (2019)
- [Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learning](https://mlsanity.com/paper/1704.03976/) (2017)
- [Panoptic Feature Pyramid Networks](https://mlsanity.com/paper/1901.02446/) (2019)
- [Dense Contrastive Learning for Self-Supervised Visual Pre-Training](https://mlsanity.com/paper/2011.09157/) (2020)
- [PointRend: Image Segmentation as Rendering](https://mlsanity.com/paper/1912.08193/) (2019)
- [Confidence Regularized Self-Training](https://mlsanity.com/paper/1908.09822/) (2019)
- [Semi-Supervised Semantic Segmentation with Cross-Consistency Training](https://mlsanity.com/paper/2003.09005/) (2020)
- [Exploring Cross-Image Pixel Contrast for Semantic Segmentation](https://mlsanity.com/paper/2101.11939/) (2021)
- [ClassMix: Segmentation-Based Data Augmentation for Semi-Supervised Learning](https://mlsanity.com/paper/2007.07936/) (2020)
- [PseudoSeg: Designing Pseudo Labels for Semantic Segmentation](https://mlsanity.com/paper/2010.09713/) (2020)
- [Adversarial Learning for Semi-Supervised Semantic Segmentation](https://mlsanity.com/paper/1802.07934/) (2018)
- [Semi-Supervised Semantic Segmentation with High- and Low-level Consistency](https://mlsanity.com/paper/1908.05724/) (2019)
- [Unsupervised Learning of Dense Visual Representations](https://mlsanity.com/paper/2011.05499/) (2020)
- [Guided Collaborative Training for Pixel-wise Semi-Supervised Learning](https://mlsanity.com/paper/2008.05258/) (2020)
- [Contrastive Learning for Label-Efficient Semantic Segmentation](https://mlsanity.com/paper/2012.06985/) (2020)
- [DMT: Dynamic Mutual Training for Semi-Supervised Learning](https://mlsanity.com/paper/2004.08514/) (2020)
- [FeatMatch: Feature-Based Augmentation for Semi-Supervised Learning](https://mlsanity.com/paper/2007.08505/) (2020)
- [Semi-supervised Skin Lesion Segmentation via Transformation Consistent Self-ensembling Model](https://mlsanity.com/paper/1808.03887/) (2018)
- [Domain Adaptation for Semantic Segmentation via Class-Balanced Self-Training](https://mlsanity.com/paper/1810.07911/) (2018)
- [Improving Semantic Segmentation via Self-Training](https://mlsanity.com/paper/2004.14960/) (2020)

## Built on by (most cited first, 30 of 80)

- [Semi-Supervised Semantic Segmentation Using Unreliable Pseudo-Labels](https://mlsanity.com/paper/2203.03884/) (2022)
- [Revisiting Weak-to-Strong Consistency in Semi-Supervised Semantic Segmentation](https://mlsanity.com/paper/2208.09910/) (2022)
- [DatasetDM: Synthesizing Data with Perception Annotations Using Diffusion Models](https://mlsanity.com/paper/2308.06160/) (2023)
- [Grounding Everything: Emerging Localization Properties in Vision-Language Transformers](https://mlsanity.com/paper/2312.00878/) (2023)
- [Augmentation Matters: A Simple-yet-Effective Approach to Semi-supervised Semantic Segmentation](https://mlsanity.com/paper/2212.04976/) (2022)
- [UniMatch V2: Pushing the Limit of Semi-Supervised Semantic Segmentation](https://mlsanity.com/paper/2410.10777/) (2024)
- [ZeroWaste Dataset: Towards Deformable Object Segmentation in Cluttered Scenes](https://mlsanity.com/paper/2106.02740/) (2021)
- [UCC: Uncertainty guided Cross-head Co-training for Semi-Supervised Semantic Segmentation](https://mlsanity.com/paper/2205.10334/) (2022)
- [Rethinking Semi-Supervised Medical Image Segmentation: A Variance-Reduction Perspective](https://mlsanity.com/paper/2302.01735/) (2023)
- [Conflict-Based Cross-View Consistency for Semi-Supervised Semantic Segmentation](https://mlsanity.com/paper/2303.01276/) (2023)
- [Mine yOur owN Anatomy: Revisiting Medical Image Segmentation with Extremely Limited Labels](https://mlsanity.com/paper/2209.13476/) (2022)
- [Logic-induced Diagnostic Reasoning for Semi-supervised Semantic Segmentation](https://mlsanity.com/paper/2308.12595/) (2023)
- [Bootstrapping Semi-supervised Medical Image Segmentation with Anatomical-aware Contrastive Distillation](https://mlsanity.com/paper/2206.02307/) (2022)
- [Diverse Cotraining Makes Strong Semi-Supervised Segmentor](https://mlsanity.com/paper/2308.09281/) (2023)
- [Switching Temporary Teachers for Semi-Supervised Semantic Segmentation](https://mlsanity.com/paper/2310.18640/) (2023)
- [Alternate Diverse Teaching for Semi-supervised Medical Image Segmentation](https://mlsanity.com/paper/2311.17325/) (2023)
- [Learning from Future: A Novel Self-Training Framework for Semantic Segmentation](https://mlsanity.com/paper/2209.06993/) (2022)
- [Local Spatiotemporal Representation Learning for Longitudinally-consistent Neuroimage Analysis](https://mlsanity.com/paper/2206.04281/) (2022)
- [Contrastive Learning for Prompt-Based Few-Shot Language Learners](https://mlsanity.com/paper/2205.01308/) (2022)
- [A Survey on Semi-Supervised Semantic Segmentation](https://mlsanity.com/paper/2302.09899/) (2023)
- [SAM as the Guide: Mastering Pseudo-Label Refinement in Semi-Supervised Referring Expression Segmentation](https://mlsanity.com/paper/2406.01451/) (2024)
- [Semantic Segmentation with Active Semi-Supervised Learning](https://mlsanity.com/paper/2203.10730/) (2022)
- [LM-CPPF: Paraphrasing-Guided Data Augmentation for Contrastive Prompt-Based Few-Shot Fine-Tuning](https://mlsanity.com/paper/2305.18169/) (2023)
- [Towards the Uncharted: Density-Descending Feature Perturbation for Semi-supervised Semantic Segmentation](https://mlsanity.com/paper/2403.06462/) (2024)
- [Panoramic Panoptic Segmentation: Insights Into Surrounding Parsing for Mobile Agents via Unsupervised Contrastive Learning](https://mlsanity.com/paper/2206.10711/) (2022)
- [Cyclical Self-Supervision for Semi-Supervised Ejection Fraction Prediction from Echocardiogram Videos](https://mlsanity.com/paper/2210.11291/) (2022)
- [Polite Teacher: Semi-Supervised Instance Segmentation with Mutual Learning and Pseudo-Label Thresholding](https://mlsanity.com/paper/2211.03850/) (2022)
- [Semi-Supervised Semantic Segmentation Based on Pseudo-Labels: A Survey](https://mlsanity.com/paper/2403.01909/) (2024)
- [n-CPS: Generalising Cross Pseudo Supervision to n Networks for Semi-Supervised Semantic Segmentation](https://mlsanity.com/paper/2112.07528/) (2021)
- [Boosting Semi-Supervised Semantic Segmentation with Probabilistic Representations](https://mlsanity.com/paper/2210.14670/) (2022)

## Abstract (arXiv)

We present ReCo, a contrastive learning framework designed at a regional level to assist learning in semantic segmentation. ReCo performs semi-supervised or supervised pixel-level contrastive learning on a sparse set of hard negative pixels, with minimal additional memory footprint. ReCo is easy to implement, being built on top of off-the-shelf segmentation networks, and consistently improves performance in both semi-supervised and supervised semantic segmentation methods, achieving smoother segmentation boundaries and faster convergence. The strongest effect is in semi-supervised learning with very few labels. With ReCo, we achieve high-quality semantic segmentation models, requiring only 5 examples of each semantic class. Code is available at https://github.com/lorenmt/reco.