# Multi-scale and Cross-scale Contrastive Learning for Semantic Segmentation

arXiv: https://arxiv.org/abs/2203.13409 · HTML: https://mlsanity.com/paper/2203.13409/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 43 of its 49 references that are in the map.
- First posted on arXiv 25 Mar 2022.

## Builds on (most cited first, 30 of 43)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [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)
- [Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1802.02611/) (2018)
- [SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers](https://mlsanity.com/paper/2105.15203/) (2021)
- [Supervised Contrastive Learning](https://mlsanity.com/paper/2004.11362/) (2020)
- [Rethinking Atrous Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1706.05587/) (2017)
- [Vision Transformers for Dense Prediction](https://mlsanity.com/paper/2103.13413/) (2021)
- [Deep High-Resolution Representation Learning for Visual Recognition](https://mlsanity.com/paper/1908.07919/) (2019)
- [Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hypersphere](https://mlsanity.com/paper/2005.10242/) (2020)
- [Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers](https://mlsanity.com/paper/2012.15840/) (2020)
- [Learning deep representations by mutual information estimation and maximization](https://mlsanity.com/paper/1808.06670/) (2018)
- [Unified Perceptual Parsing for Scene Understanding](https://mlsanity.com/paper/1807.10221/) (2018)
- [Semantic Understanding of Scenes through the ADE20K Dataset](https://mlsanity.com/paper/1608.05442/) (2016)
- [Segmenter: Transformer for Semantic Segmentation](https://mlsanity.com/paper/2105.05633/) (2021)
- [Learning Representations by Maximizing Mutual Information Across Views](https://mlsanity.com/paper/1906.00910/) (2019)
- [Training Region-based Object Detectors with Online Hard Example Mining](https://mlsanity.com/paper/1604.03540/) (2016)
- [Segmentation Transformer: Object-Contextual Representations for Semantic Segmentation](https://mlsanity.com/paper/1909.11065/) (2019)
- [Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs](https://mlsanity.com/paper/1412.7062/) (2014)
- [A Theoretical Analysis of Contrastive Unsupervised Representation Learning](https://mlsanity.com/paper/1902.09229/) (2019)
- [Dense Contrastive Learning for Self-Supervised Visual Pre-Training](https://mlsanity.com/paper/2011.09157/) (2020)
- [ResNeSt: Split-Attention Networks](https://mlsanity.com/paper/2004.08955/) (2020)
- [Hard Negative Mixing for Contrastive Learning](https://mlsanity.com/paper/2010.01028/) (2020)
- [Contrastive learning of global and local features for medical image segmentation with limited annotations](https://mlsanity.com/paper/2006.10511/) (2020)
- [Dilated Residual Networks](https://mlsanity.com/paper/1705.09914/) (2017)

## Built on by (most cited first, 8 of 8)

- [Efficient Vision-Language Pretraining with Visual Concepts and Hierarchical Alignment](https://mlsanity.com/paper/2208.13628/) (2022)
- [Contextrast: Contextual Contrastive Learning for Semantic Segmentation](https://mlsanity.com/paper/2404.10633/) (2024)
- [Edge Guided GANs with Multi-Scale Contrastive Learning for Semantic Image Synthesis](https://mlsanity.com/paper/2307.12084/) (2023)
- [Improving Anomaly Segmentation with Multi-Granularity Cross-Domain Alignment](https://mlsanity.com/paper/2308.08696/) (2023)
- [Understanding Dark Scenes by Contrasting Multi-Modal Observations](https://mlsanity.com/paper/2308.12320/) (2023)
- [Boosting Weakly-Supervised Image Segmentation via Representation, Transform, and Compensator](https://mlsanity.com/paper/2309.00871/) (2023)
- [Grounding Agentic VLMs with Dedicated Segmentation for Fine-Grained Vehicle Damage Assessment](https://mlsanity.com/paper/2608.02470/) (2026)
- [Contextrast++: Robust Multi-Scale Contextual Contrastive Learning for Semantic Segmentation](https://mlsanity.com/paper/2608.22679/) (2026)

## Abstract (arXiv)

This work considers supervised contrastive learning for semantic segmentation. We apply contrastive learning to enhance the discriminative power of the multi-scale features extracted by semantic segmentation networks. Our key methodological insight is to leverage samples from the feature spaces emanating from multiple stages of a model's encoder itself requiring neither data augmentation nor online memory banks to obtain a diverse set of samples. To allow for such an extension we introduce an efficient and effective sampling process, that enables applying contrastive losses over the encoder's features at multiple scales. Furthermore, by first mapping the encoder's multi-scale representations to a common feature space, we instantiate a novel form of supervised local-global constraint by introducing cross-scale contrastive learning linking high-resolution local features to low-resolution global features. Combined, our multi-scale and cross-scale contrastive losses boost performance of various models (DeepLabV3, HRNet, OCRNet, UPerNet) with both CNN and Transformer backbones, when evaluated on 4 diverse datasets from natural (Cityscapes, PascalContext, ADE20K) but also surgical (CaDIS) domains. Our code is available at https://github.com/RViMLab/MS_CS_ContrSeg. datasets from natural (Cityscapes, PascalContext, ADE20K) but also surgical (CaDIS) domains.