mlsanityData to 7 Oct 2026

Self-EMD: Self-Supervised Object Detection without ImageNet

arXiv 2011.13677 ↗First posted 27 Nov 2020cs.CVcited by 70

Not on the map. Why?

Abstract (arXiv)

In this paper, we propose a novel self-supervised representation learning method, Self-EMD, for object detection. Our method directly trained on unlabeled non-iconic image dataset like COCO, instead of commonly used iconic-object image dataset like ImageNet. We keep the convolutional feature maps as the image embedding to preserve spatial structures and adopt Earth Mover's Distance (EMD) to compute the similarity between two embeddings. Our Faster R-CNN (ResNet50-FPN) baseline achieves 39.8% mAP on COCO, which is on par with the state of the art self-supervised methods pre-trained on ImageNet. More importantly, it can be further improved to 40.4% mAP with more unlabeled images, showing its great potential for leveraging more easily obtained unlabeled data. Code will be made available.

Key facts. Cited by 70 papers in the map (data through 7 Oct 2026). First posted on arXiv 27 Nov 2020.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 12; 2022: 23; 2023: 20; 2024: 10; 2025: 5.

70 papers.

Sort:

By area:

  1. 2022SPot-the-Difference Self-Supervised Pre-training for Anomaly Detection and Segmentationcited by 397
  2. 2022CroCo: Self-Supervised Pre-training for 3D Vision Tasks by Cross-View Completioncited by 158
  3. 2021MST: Masked Self-Supervised Transformer for Visual Representationcited by 114
  4. 2021Aligning Pretraining for Detection via Object-Level Contrastive Learningcited by 110
  5. 2022Self-Supervised Learning of Object Parts for Semantic Segmentationcited by 90
  6. 2023Towards Large-scale 3D Representation Learning with Multi-dataset Point Prompt Trainingcited by 85
  7. 2022Siamese Image Modeling for Self-Supervised Vision Representation Learningcited by 78
  8. 2021Unsupervised Object-Level Representation Learning from Scene Imagescited by 72
  9. 2022Self-Supervised Visual Representation Learning with Semantic Groupingcited by 70
  10. 2021Unsupervised Domain Adaptive 3D Detection with Multi-Level Consistencycited by 63
  11. 2021Do Different Tracking Tasks Require Different Appearance Models?cited by 62
  12. 2022Hyperbolic Contrastive Learning for Visual Representations beyond Objectscited by 58
38 more
  1. 2023Masked Scene Contrast: A Scalable Framework for Unsupervised 3D Representation Learningcited by 55
  2. 2022Understanding Masked Image Modeling via Learning Occlusion Invariant Featurecited by 50
  3. 2023CMID: A Unified Self-Supervised Learning Framework for Remote Sensing Image Understandingcited by 48
  4. 2022Point-Level Region Contrast for Object Detection Pre-Trainingcited by 41
  5. 2022Learning Super-Features for Image Retrievalcited by 35
  6. 2022Dense Learning based Semi-Supervised Object Detectioncited by 32
  7. 2022UniVIP: A Unified Framework for Self-Supervised Visual Pre-trainingcited by 30
  8. 2022Versatile Multi-Modal Pre-Training for Human-Centric Perceptioncited by 26
  9. 2024GroupContrast: Semantic-aware Self-supervised Representation Learning for 3D Understandingcited by 26
  10. 2021Object-Aware Cropping for Self-Supervised Learningcited by 22
  11. 2023CrOC: Cross-View Online Clustering for Dense Visual Representation Learningcited by 21
  12. 2022Partially Does It: Towards Scene-Level FG-SBIR with Partial Inputcited by 20
  13. 2023Semantics Meets Temporal Correspondence: Self-supervised Object-centric Learning in Videoscited by 20
  14. 2023Multi-Label Self-Supervised Learning with Scene Imagescited by 17
  15. 2023CrIBo: Self-Supervised Learning via Cross-Image Object-Level Bootstrappingcited by 17
  16. 2024Near, far: Patch-ordering enhances vision foundation models' scene understandingcited by 15
  17. 2023AlignDet: Aligning Pre-training and Fine-tuning in Object Detectioncited by 14
  18. 2024Crowd-SAM: SAM as a Smart Annotator for Object Detection in Crowded Scenescited by 13
  19. 2022RoSA: A Robust Self-Aligned Framework for Node-Node Graph Contrastive Learningcited by 12
  20. 2021Semantic-Aware Generation for Self-Supervised Visual Representation Learningcited by 11
  21. 2022ConCL: Concept Contrastive Learning for Dense Prediction Pre-training in Pathology Imagescited by 11
  22. 2021Deeply Unsupervised Patch Re-Identification for Pre-training Object Detectorscited by 9
  23. 2021Exploring Localization for Self-supervised Fine-grained Contrastive Learningcited by 9
  24. 2023Self-Supervised Representation Learning from Temporal Ordering of Automated Driving Sequencescited by 9
  25. 2023SelfDocSeg: A Self-Supervised vision-based Approach towards Document Segmentationcited by 7
  26. 2023Introspective Deep Metric Learningcited by 7
  27. 2023Prospective Role of Foundation Models in Advancing Autonomous Vehiclescited by 7
  28. 2023DenseDINO: Boosting Dense Self-Supervised Learning with Token-Based Point-Level Consistencycited by 6
  29. 2022DATA: Domain-Aware and Task-Aware Self-supervised Learningcited by 5
  30. 2022Pixel-Wise Contrastive Distillationcited by 5
  31. 2023Coarse Is Better? A New Pipeline Towards Self-Supervised Learning with Uncurated Imagescited by 5
  32. 2023PAD: Self-Supervised Pre-Training with Patchwise-Scale Adapter for Infrared Imagescited by 5
  33. 2021Residual Contrastive Learning for Image Reconstruction: Learning Transferable Representations from Noisy Imagescited by 3
  34. 2022CoDo: Contrastive Learning with Downstream Background Invariance for Detectioncited by 3
  35. 2022OPERA: Omni-Supervised Representation Learning with Hierarchical Supervisionscited by 3
  36. 2022Local Manifold Augmentation for Multiview Semantic Consistencycited by 3
  37. 2023De-coupling and De-positioning Dense Self-supervised Learningcited by 3
  38. 2024LeOCLR: Leveraging Original Images for Contrastive Learning of Visual Representationscited by 3

50 most cited of 70 All 70 (JSON)