mlsanityData to 7 Oct 2026

Equalization Loss for Long-Tailed Object Recognition

arXiv 2003.05176 ↗First posted 11 Mar 2020cs.CVcited by 285

Not on the map. Why?

Abstract (arXiv)

Object recognition techniques using convolutional neural networks (CNN) have achieved great success. However, state-of-the-art object detection methods still perform poorly on large vocabulary and long-tailed datasets, e.g. LVIS. In this work, we analyze this problem from a novel perspective: each positive sample of one category can be seen as a negative sample for other categories, making the tail categories receive more discouraging gradients. Based on it, we propose a simple but effective loss, named equalization loss, to tackle the problem of long-tailed rare categories by simply ignoring those gradients for rare categories. The equalization loss protects the learning of rare categories from being at a disadvantage during the network parameter updating. Thus the model is capable of learning better discriminative features for objects of rare classes. Without any bells and whistles, our method achieves AP gains of 4.1% and 4.8% for the rare and common categories on the challenging LVIS benchmark, compared to the Mask R-CNN baseline. With the utilization of the effective equalization loss, we finally won the 1st place in the LVIS Challenge 2019. Code has been made available at: https: //github.com/tztztztztz/eql.detectron2

Key facts. Cited by 285 papers in the map (data through 7 Oct 2026). First posted on arXiv 11 Mar 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 54; 2022: 68; 2023: 59; 2024: 51; 2025: 30; 2026: 23.

285 papers.

Sort:

By area:

  1. 2021MDETR -- Modulated Detection for End-to-End Multi-Modal Understandingcited by 811
  2. 2022Detecting Twenty-thousand Classes using Image-level Supervisioncited by 613
  3. 2023End-to-end Autonomous Driving: Challenges and Frontierscited by 485
  4. 2021Deep Long-Tailed Learning: A Surveycited by 416
  5. 2022DiffusionDet: Diffusion Model for Object Detectioncited by 354
  6. 2021Parametric Contrastive Learningcited by 217
  7. 2021Distribution Alignment: A Unified Framework for Long-tail Visual Recognitioncited by 198
  8. 2022MeMViT: Memory-Augmented Multiscale Vision Transformer for Efficient Long-Term Video Recognitioncited by 189
  9. 2021CReST: A Class-Rebalancing Self-Training Framework for Imbalanced Semi-Supervised Learningcited by 174
  10. 2023Towards Open Vocabulary Learning: A Surveycited by 165
  11. 2021Reviving Iterative Training with Mask Guidance for Interactive Segmentationcited by 162
  12. 2022Balanced Contrastive Learning for Long-Tailed Visual Recognitioncited by 143
38 more
  1. 2021Bipartite Graph Network with Adaptive Message Passing for Unbiased Scene Graph Generationcited by 137
  2. 2021Probabilistic two-stage detectioncited by 130
  3. 2021Contrastive Learning based Hybrid Networks for Long-Tailed Image Classificationcited by 130
  4. 2021Simple multi-dataset detectioncited by 126
  5. 2024VideoPrism: A Foundational Visual Encoder for Video Understandingcited by 103
  6. 2022Animal Kingdom: A Large and Diverse Dataset for Animal Behavior Understandingcited by 102
  7. 2021ResLT: Residual Learning for Long-tailed Recognitioncited by 96
  8. 2021Self-Supervised Aggregation of Diverse Experts for Test-Agnostic Long-Tailed Recognitioncited by 95
  9. 2021FASA: Feature Augmentation and Sampling Adaptation for Long-Tailed Instance Segmentationcited by 76
  10. 2022A Survey on Long-Tailed Visual Recognitioncited by 75
  11. 2023Long-tailed Visual Recognition via Gaussian Clouded Logit Adjustmentcited by 75
  12. 2021Label-Imbalanced and Group-Sensitive Classification under Overparameterizationcited by 74
  13. 2021Self Supervision to Distillation for Long-Tailed Visual Recognitioncited by 73
  14. 2021Distilling Virtual Examples for Long-tailed Recognitioncited by 72
  15. 2022LPT: Long-tailed Prompt Tuning for Image Classificationcited by 69
  16. 2021VL-LTR: Learning Class-wise Visual-Linguistic Representation for Long-Tailed Visual Recognitioncited by 65
  17. 2022Nested Collaborative Learning for Long-Tailed Visual Recognitioncited by 63
  18. 2021DeepSMOTE: Fusing Deep Learning and SMOTE for Imbalanced Datacited by 62
  19. 2023Detecting Everything in the Open World: Towards Universal Object Detectioncited by 62
  20. 2022Real-time Online Video Detection with Temporal Smoothing Transformerscited by 58
  21. 2023Decoupled Kullback-Leibler Divergence Losscited by 58
  22. 2021Evaluating Large-Vocabulary Object Detectors: The Devil is in the Detailscited by 57
  23. 2021Adaptive Class Suppression Loss for Long-Tail Object Detectioncited by 55
  24. 2021Exploring Classification Equilibrium in Long-Tailed Object Detectioncited by 51
  25. 2022DiffusionInst: Diffusion Model for Instance Segmentationcited by 49
  26. 2022Equalized Focal Loss for Dense Long-Tailed Object Detectioncited by 46
  27. 2022Generalized Parametric Contrastive Learningcited by 45
  28. 2022Neural Collapse Inspired Attraction-Repulsion-Balanced Loss for Imbalanced Learningcited by 43
  29. 2024Probabilistic Contrastive Learning for Long-Tailed Visual Recognitioncited by 42
  30. 2022TAM: Topology-Aware Margin Loss for Class-Imbalanced Node Classificationcited by 41
  31. 2021On Model Calibration for Long-Tailed Object Detection and Instance Segmentationcited by 39
  32. 2021Towards Calibrated Model for Long-Tailed Visual Recognition from Prior Perspectivecited by 39
  33. 2021Disentangle Your Dense Object Detectorcited by 37
  34. 2024Gradient Reweighting: Towards Imbalanced Class-Incremental Learningcited by 37
  35. 2021VideoLT: Large-scale Long-tailed Video Recognitioncited by 35
  36. 2021Robust Long-Tailed Learning under Label Noisecited by 35
  37. 2023Exploring Vision-Language Models for Imbalanced Learningcited by 35
  38. 2023MosaicFusion: Diffusion Models as Data Augmenters for Large Vocabulary Instance Segmentationcited by 35

50 most cited of 285 All 285 (JSON)