mlsanityData to 7 Oct 2026

Contextrast: Contextual Contrastive Learning for Semantic Segmentation

arXiv 2404.10633 ↗First posted 16 Apr 2024cs.CVcited by 12

Not on the map. Why?

Abstract (arXiv)

Despite great improvements in semantic segmentation, challenges persist because of the lack of local/global contexts and the relationship between them. In this paper, we propose Contextrast, a contrastive learning-based semantic segmentation method that allows to capture local/global contexts and comprehend their relationships. Our proposed method comprises two parts: a) contextual contrastive learning (CCL) and b) boundary-aware negative (BANE) sampling. Contextual contrastive learning obtains local/global context from multi-scale feature aggregation and inter/intra-relationship of features for better discrimination capabilities. Meanwhile, BANE sampling selects embedding features along the boundaries of incorrectly predicted regions to employ them as harder negative samples on our contrastive learning, resolving segmentation issues along the boundary region by exploiting fine-grained details. We demonstrate that our Contextrast substantially enhances the performance of semantic segmentation networks, outperforming state-of-the-art contrastive learning approaches on diverse public datasets, e.g. Cityscapes, CamVid, PASCAL-C, COCO-Stuff, and ADE20K, without an increase in computational cost during inference.

Key facts. Cited by 12 papers in the map (data through 7 Oct 2026). Builds on 47 of its 56 references that are in the map. First posted on arXiv 16 Apr 2024.

Builds on

47 of 56 references.

References · 47

  1. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  2. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  3. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,845
  4. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
  5. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,239
  6. 2018Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentationcited by 3,210
  7. 2015FaceNet: A Unified Embedding for Face Recognition and Clusteringcited by 2,833
  8. 2020Supervised Contrastive Learningcited by 2,803
  9. 2016Pyramid Scene Parsing Networkcited by 2,472
  10. 2017Rethinking Atrous Convolution for Semantic Image Segmentationcited by 2,154
  11. 2019Deep High-Resolution Representation Learning for Visual Recognitioncited by 1,417
  12. 2018Unified Perceptual Parsing for Scene Understandingcited by 1,265
35 more
  1. 2018Dual Attention Network for Scene Segmentationcited by 1,001
  2. 2016COCO-Stuff: Thing and Stuff Classes in Contextcited by 858
  3. 2021Segmenter: Transformer for Semantic Segmentationcited by 855
  4. 2023ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoderscited by 703
  5. 2019Segmentation Transformer: Object-Contextual Representations for Semantic Segmentationcited by 573
  6. 2014Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFscited by 552
  7. 2022InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutionscited by 479
  8. 2020Hard Negative Mixing for Contrastive Learningcited by 399
  9. 2021Exploring Cross-Image Pixel Contrast for Semantic Segmentationcited by 242
  10. 2019High-Resolution Representations for Labeling Pixels and Regionscited by 211
  11. 2018Pyramid Attention Network for Semantic Segmentationcited by 148
  12. 2021Targeted Supervised Contrastive Learning for Long-Tailed Recognitioncited by 132
  13. 2020Context Prior for Scene Segmentationcited by 121
  14. 2018Learning a Discriminative Feature Network for Semantic Segmentationcited by 114
  15. 2020SegFix: Model-Agnostic Boundary Refinement for Segmentationcited by 97
  16. 2021Deep Dual-resolution Networks for Real-time and Accurate Semantic Segmentation of Road Scenescited by 89
  17. 2022Deep Hierarchical Semantic Segmentationcited by 84
  18. 2022PIDNet: A Real-time Semantic Segmentation Network Inspired by PID Controllerscited by 84
  19. 2020Cars Can't Fly up in the Sky: Improving Urban-Scene Segmentation via Height-driven Attention Networkscited by 70
  20. 2019Semantic Correlation Promoted Shape-Variant Context for Segmentationcited by 61
  21. 2019Dual Graph Convolutional Network for Semantic Segmentationcited by 59
  22. 2022Stepwise Feature Fusion: Local Guides Globalcited by 56
  23. 2020Are all negatives created equal in contrastive instance discrimination?cited by 50
  24. 2018Adaptive Affinity Fields for Semantic Segmentationcited by 48
  25. 2023Understanding Imbalanced Semantic Segmentation Through Neural Collapsecited by 46
  26. 2021Active Boundary Loss for Semantic Segmentationcited by 40
  27. 2020Delving into Inter-Image Invariance for Unsupervised Visual Representationscited by 37
  28. 2022FCN-Transformer Feature Fusion for Polyp Segmentationcited by 37
  29. 2021Progressive Semantic Segmentationcited by 35
  30. 2023Semantic Diffusion Network for Semantic Segmentationcited by 30
  31. 2023Using DUCK-Net for Polyp Image Segmentationcited by 30
  32. 2022ColonFormer: An Efficient Transformer based Method for Colon Polyp Segmentationcited by 28
  33. 2024Semantic Scene Segmentation for Roboticscited by 16
  34. 2022Multi-scale and Cross-scale Contrastive Learning for Semantic Segmentationcited by 8
  35. 2021Semantic Scene Segmentation for Robotics Applicationscited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 4; 2025: 5; 2026: 3.

12 papers.

  1. 2024Uncertainty-Participation Context Consistency Learning for Semi-supervised Semantic Segmentationcited by 6
  2. 2025Selective Contrastive Learning for Weakly Supervised Affordance Groundingcited by 6
  3. 2025Revisiting Efficient Semantic Segmentation: Learning Offsets for Better Spatial and Class Feature Alignmentcited by 5
  4. 2025Divide, Conquer and Unite: Hierarchical Style-Recalibrated Prototype Alignment for Federated Medical Segmentationcited by 2
  5. 2024Outlier-Robust Long-Term Robotic Mapping Leveraging Ground Segmentationcited by 1
  6. 2024Efficient Fourier Filtering Network with Contrastive Learning for AAV-based Unaligned Bimodal Salient Object Detectioncited by 1
  7. 2024AFANet: Adaptive Frequency-Aware Network for Weakly-Supervised Few-Shot Semantic Segmentationcited by 1
  8. 2025Video-Based MPAA Rating Prediction: An Attention-Driven Hybrid Architecture Using Contrastive Learningcited by 0
  9. 2025OMUDA: Omni-level Masking for Unsupervised Domain Adaptation in Semantic Segmentationcited by 0
  10. 2026Intra-Class Subdivision for Pixel Contrastive Learning: Application to Semi-supervised Cardiac Image Segmentationcited by 0
  11. 2026Grounding Agentic VLMs with Dedicated Segmentation for Fine-Grained Vehicle Damage Assessmentcited by 0
  12. 2026Contextrast++: Robust Multi-Scale Contextual Contrastive Learning for Semantic Segmentationcited by 0