mlsanityData to 14 Oct 2026

Self-Supervised Learning for Image Segmentation: A Comprehensive Survey

arXiv 2505.13584 ↗First posted 19 May 2025cs.CVcited by 3

Not on the map. Why?

Abstract (arXiv)

Supervised learning demands large amounts of precisely annotated data to achieve promising results. Such data curation is labor-intensive and imposes significant overhead regarding time and costs. Self-supervised learning (SSL) partially overcomes these limitations by exploiting vast amounts of unlabeled data and creating surrogate (pretext or proxy) tasks to learn useful representations without manual labeling. As a result, SSL has become a powerful machine learning (ML) paradigm for solving several practical downstream computer vision problems, such as classification, detection, and segmentation. Image segmentation is the cornerstone of many high-level visual perception applications, including medical imaging, intelligent transportation, agriculture, and surveillance. Although there is substantial research potential for developing advanced algorithms for SSL-based semantic segmentation, a comprehensive study of existing methodologies is essential to trace advances and guide emerging researchers. This survey thoroughly investigates over 150 recent image segmentation articles, particularly focusing on SSL. It provides a practical categorization of pretext tasks, downstream tasks, and commonly used benchmark datasets for image segmentation research. It concludes with key observations distilled from a large body of literature and offers future directions to make this research field more accessible and comprehensible for readers.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 101 of its 177 references that are in the map. First posted on arXiv 19 May 2025.

Builds on

101 of 177 references.

References · 101

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  2. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  3. 2018Representation Learning with Contrastive Predictive Codingcited by 7,777
  4. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,513
  5. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,444
  6. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,241
  7. 2020Exploring Simple Siamese Representation Learningcited by 2,866
  8. 2020Unsupervised Learning of Visual Features by Contrasting Cluster Assignmentscited by 2,857
  9. 2019ALBERT: A Lite BERT for Self-supervised Learning of Language Representationscited by 2,790
  10. 2013Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distancescited by 2,316
  11. 2020Improved Baselines with Momentum Contrastive Learningcited by 2,287
  12. 2021An Empirical Study of Training Self-Supervised Vision Transformerscited by 1,616
38 more
  1. 2018Unsupervised Representation Learning by Predicting Image Rotationscited by 1,591
  2. 2016Context Encoders: Feature Learning by Inpaintingcited by 1,428
  3. 2016Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzlescited by 1,382
  4. 2018Learning deep representations by mutual information estimation and maximizationcited by 1,273
  5. 2016Colorful Image Colorizationcited by 1,114
  6. 2022Diffusion Models in Vision: A Surveycited by 1,015
  7. 2016COCO-Stuff: Thing and Stuff Classes in Contextcited by 864
  8. 2019Self-Supervised Learning of Pretext-Invariant Representationscited by 808
  9. 2018Panoptic Segmentationcited by 802
  10. 2020Self-supervised Learning: Generative or Contrastivecited by 694
  11. 2019Data-Efficient Image Recognition with Contrastive Predictive Codingcited by 673
  12. 2019Skin Lesion Analysis Toward Melanoma Detection 2018: A Challenge Hosted by the International Skin Imaging Collaboration (ISIC)cited by 669
  13. 2020Image Segmentation Using Deep Learning: A Surveycited by 660
  14. 2019Self-supervised Visual Feature Learning with Deep Neural Networks: A Surveycited by 657
  15. 2020Dense Contrastive Learning for Self-Supervised Visual Pre-Trainingcited by 512
  16. 2015Unsupervised Learning of Video Representations using LSTMscited by 435
  17. 2022SPot-the-Difference Self-Supervised Pre-training for Anomaly Detection and Segmentationcited by 400
  18. 2019S4L: Self-Supervised Semi-Supervised Learningcited by 335
  19. 2021Big Self-Supervised Models Advance Medical Image Classificationcited by 320
  20. 2020Contrastive learning of global and local features for medical image segmentation with limited annotationscited by 309
  21. 2020Propagate Yourself: Exploring Pixel-Level Consistency for Unsupervised Visual Representation Learningcited by 297
  22. 2020Prior Guided Feature Enrichment Network for Few-Shot Segmentationcited by 271
  23. 2016Learning Representations for Automatic Colorizationcited by 251
  24. 2019ResUNet++: An Advanced Architecture for Medical Image Segmentationcited by 211
  25. 2023A Survey on Self-supervised Learning: Algorithms, Applications, and Future Trendscited by 207
  26. 2020Unsupervised Intra-domain Adaptation for Semantic Segmentation through Self-Supervisioncited by 198
  27. 2019The state of the art in kidney and kidney tumor segmentation in contrast-enhanced CT imaging: Results of the KiTS19 Challengecited by 190
  28. 2020Self-Supervised Learning of Audio-Visual Objects from Videocited by 188
  29. 2018Adversarial Learning for Semi-Supervised Semantic Segmentationcited by 173
  30. 2020Single-Stage Semantic Segmentation from Image Labelscited by 167
  31. 2021Self-supervised Augmentation Consistency for Adapting Semantic Segmentationcited by 149
  32. 2020Anomaly Detection in Video via Self-Supervised and Multi-Task Learningcited by 148
  33. 2021Semantic Segmentation with Generative Models: Semi-Supervised Learning and Strong Out-of-Domain Generalizationcited by 141
  34. 2022Self-supervised Learning in Remote Sensing: A Reviewcited by 137
  35. 2019Deep learning for cardiac image segmentation: A reviewcited by 131
  36. 2016Fully Convolutional Instance-aware Semantic Segmentationcited by 123
  37. 2021Self-Supervised Learning with Swin Transformerscited by 122
  38. 2023The KiTS21 Challenge: Automatic segmentation of kidneys, renal tumors, and renal cysts in corticomedullary-phase CTcited by 103

50 most cited of 101 All 101 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 2.

3 papers.

  1. 2025Dual Atrous Separable Convolution for Improving Agricultural Semantic Segmentationcited by 1
  2. 2026Scale-Aware Self-Supervised Learning for Segmentation of Small and Sparse Structurescited by 0
  3. 2026DAS-SK: An Adaptive Model Integrating Dual Atrous Separable and Selective Kernel CNN for Agriculture Semantic Segmentationcited by 0