mlsanityData to 7 Oct 2026

Self-supervised Learning with Local Contrastive Loss for Detection and Semantic Segmentation

arXiv 2207.04398 ↗First posted 10 Jul 2022cs.CV cs.AIcited by 8

Not on the map. Why?

Abstract (arXiv)

We present a self-supervised learning (SSL) method suitable for semi-global tasks such as object detection and semantic segmentation. We enforce local consistency between self-learned features, representing corresponding image locations of transformed versions of the same image, by minimizing a pixel-level local contrastive (LC) loss during training. LC-loss can be added to existing self-supervised learning methods with minimal overhead. We evaluate our SSL approach on two downstream tasks -- object detection and semantic segmentation, using COCO, PASCAL VOC, and CityScapes datasets. Our method outperforms the existing state-of-the-art SSL approaches by 1.9% on COCO object detection, 1.4% on PASCAL VOC detection, and 0.6% on CityScapes segmentation.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 39 of its 47 references that are in the map. First posted on arXiv 10 Jul 2022.

Builds on

39 of 47 references.

References · 39

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  3. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  4. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  5. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
  6. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,893
  7. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,845
  8. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,712
  9. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
  10. 2020Unsupervised Learning of Visual Features by Contrasting Cluster Assignmentscited by 2,845
  11. 2020Improved Baselines with Momentum Contrastive Learningcited by 2,282
  12. 2013Describing Textures in the Wildcited by 2,110
27 more
  1. 2018Unsupervised Representation Learning by Predicting Image Rotationscited by 1,586
  2. 2017EuroSAT: A Novel Dataset and Deep Learning Benchmark for Land Use and Land Cover Classificationcited by 1,488
  3. 2016Context Encoders: Feature Learning by Inpaintingcited by 1,424
  4. 2019MMDetection: Open MMLab Detection Toolbox and Benchmarkcited by 1,379
  5. 2020Big Self-Supervised Models are Strong Semi-Supervised Learnerscited by 1,375
  6. 2018Unified Perceptual Parsing for Scene Understandingcited by 1,265
  7. 2016Colorful Image Colorizationcited by 1,113
  8. 2015Unsupervised Visual Representation Learning by Context Predictioncited by 1,062
  9. 2019Learning Robust Global Representations by Penalizing Local Predictive Powercited by 1,010
  10. 2020What Makes for Good Views for Contrastive Learning?cited by 843
  11. 2017Focal Loss for Dense Object Detectioncited by 749
  12. 2019Data-Efficient Image Recognition with Contrastive Predictive Codingcited by 672
  13. 2019Skin Lesion Analysis Toward Melanoma Detection 2018: A Challenge Hosted by the International Skin Imaging Collaboration (ISIC)cited by 657
  14. 2020Dense Contrastive Learning for Self-Supervised Visual Pre-Trainingcited by 512
  15. 2018Rethinking ImageNet Pre-trainingcited by 376
  16. 2020Propagate Yourself: Exploring Pixel-Level Consistency for Unsupervised Visual Representation Learningcited by 297
  17. 2016Using Deep Learning for Image-Based Plant Disease Detectioncited by 216
  18. 2021DetCo: Unsupervised Contrastive Learning for Object Detectioncited by 205
  19. 2019Scaling and Benchmarking Self-Supervised Visual Representation Learningcited by 201
  20. 2021Efficient Visual Pretraining with Contrastive Detectioncited by 150
  21. 2020Unsupervised Learning of Dense Visual Representationscited by 147
  22. 2021Aligning Pretraining for Detection via Object-Level Contrastive Learningcited by 110
  23. 2021Instance Localization for Self-supervised Detection Pretrainingcited by 99
  24. 2021Region Similarity Representation Learningcited by 96
  25. 2021A Broad Study on the Transferability of Visual Representations with Contrastive Learningcited by 78
  26. 2021Spatially Consistent Representation Learningcited by 64
  27. 2021Visual Correspondence Hallucinationcited by 5

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 2; 2024: 3; 2025: 2.

8 papers.

  1. 2023FLSL: Feature-level Self-supervised Learningcited by 9
  2. 2025Self-Supervised Learning for Image Segmentation: A Comprehensive Surveycited by 3
  3. 2024Multi-Grained Contrast for Data-Efficient Unsupervised Representation Learningcited by 2
  4. 2024Self-Supervised Learning for Real-World Object Detection: a Surveycited by 2
  5. 2024PARMESAN: Parameter-Free Memory Search and Transduction for Dense Prediction Taskscited by 1
  6. 2022Label-Efficient Object Detection via Region Proposal Network Pre-Trainingcited by 0
  7. 2023Aligned Unsupervised Pretraining of Object Detectors with Self-trainingcited by 0
  8. 2025Multiple Object Stitching for Unsupervised Representation Learningcited by 0