mlsanityData to 7 Oct 2026

Long-tail Detection with Effective Class-Margins

arXiv 2301.09724 ↗First posted 23 Jan 2023cs.CV cs.LGcited by 13

Not on the map. Why?

Abstract (arXiv)

Large-scale object detection and instance segmentation face a severe data imbalance. The finer-grained object classes become, the less frequent they appear in our datasets. However, at test-time, we expect a detector that performs well for all classes and not just the most frequent ones. In this paper, we provide a theoretical understanding of the long-trail detection problem. We show how the commonly used mean average precision evaluation metric on an unknown test set is bound by a margin-based binary classification error on a long-tailed object detection training set. We optimize margin-based binary classification error with a novel surrogate objective called Effective Class-Margin Loss (ECM). The ECM loss is simple, theoretically well-motivated, and outperforms other heuristic counterparts on LVIS v1 benchmark over a wide range of architecture and detectors. Code is available at urlhttps://github.com/janghyuncho/ECM-Loss.

Key facts. Cited by 13 papers in the map (data through 7 Oct 2026). Builds on 45 of its 55 references that are in the map. First posted on arXiv 23 Jan 2023.

Builds on

45 of 55 references.

References · 45

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  3. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  4. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  5. 2020End-to-End Object Detection with Transformerscited by 7,384
  6. 2017Mask R-CNNcited by 7,259
  7. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  8. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,829
  9. 2015Fast R-CNNcited by 2,930
  10. 2018YOLOv3: An Incremental Improvementcited by 2,652
  11. 2019FCOS: Fully Convolutional One-Stage Object Detectioncited by 1,573
  12. 2016YOLO9000: Better, Faster, Strongercited by 1,429
33 more
  1. 2019MMDetection: Open MMLab Detection Toolbox and Benchmarkcited by 1,379
  2. 2017Cascade R-CNN: Delving into High Quality Object Detectioncited by 1,275
  3. 2019LVIS: A Dataset for Large Vocabulary Instance Segmentationcited by 1,215
  4. 2019Objects as Pointscited by 1,172
  5. 2019Learning Imbalanced Datasets with Label-Distribution-Aware Margin Losscited by 987
  6. 2019Decoupling Representation and Classifier for Long-Tailed Recognitioncited by 806
  7. 2017Spectrally-normalized margin bounds for neural networkscited by 681
  8. 2020Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentationcited by 595
  9. 2018The Open Images Dataset V4: Unified image classification, object detection, and visual relationship detection at scalecited by 542
  10. 2019Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selectioncited by 539
  11. 2020Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detectioncited by 408
  12. 2016Large-Margin Softmax Loss for Convolutional Neural Networkscited by 296
  13. 2020Equalization Loss for Long-Tailed Object Recognitioncited by 285
  14. 2018Additive Margin Softmax for Face Verificationcited by 275
  15. 2020Long-Tailed Classification by Keeping the Good and Removing the Bad Momentum Causal Effectcited by 256
  16. 2020VarifocalNet: An IoU-aware Dense Object Detectorcited by 230
  17. 2021Distribution Alignment: A Unified Framework for Long-tail Visual Recognitioncited by 198
  18. 2021Boundary IoU: Improving Object-Centric Image Segmentation Evaluationcited by 186
  19. 2020Overcoming Classifier Imbalance for Long-tail Object Detection with Balanced Group Softmaxcited by 152
  20. 2020Seesaw Loss for Long-Tailed Instance Segmentationcited by 146
  21. 2021Probabilistic two-stage detectioncited by 130
  22. 2021Simple multi-dataset detectioncited by 126
  23. 2020The Devil is in Classification: A Simple Framework for Long-tail Object Detection and Instance Segmentationcited by 108
  24. 2020Equalization Loss v2: A New Gradient Balance Approach for Long-tailed Object Detectioncited by 99
  25. 2019Optimizing Rank-based Metrics with Blackbox Differentiationcited by 58
  26. 2021Evaluating Large-Vocabulary Object Detectors: The Devil is in the Detailscited by 57
  27. 2021Exploring Classification Equilibrium in Long-Tailed Object Detectioncited by 51
  28. 2020Forest R-CNN: Large-Vocabulary Long-Tailed Object Detection and Instance Segmentationcited by 41
  29. 2021MosaicOS: A Simple and Effective Use of Object-Centric Images for Long-Tailed Object Detectioncited by 33
  30. 2018Localization Recall Precision (LRP): A New Performance Metric for Object Detectioncited by 31
  31. 2020A Ranking-based, Balanced Loss Function Unifying Classification and Localisation in Object Detectioncited by 25
  32. 2020AP-Loss for Accurate One-Stage Object Detectioncited by 24
  33. 2021Rank & Sort Loss for Object Detection and Instance Segmentationcited by 22

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 4; 2024: 7; 2025: 1; 2026: 1.

13 papers.

Sort:

By area:

  1. 2023iKUN: Speak to Trackers without Retrainingcited by 31
  2. 2024A Systematic Review on Long-Tailed Learningcited by 27
  3. 2023Instance-Aware Repeat Factor Sampling for Long-Tailed Object Detectioncited by 7
  4. 2024Adaptive Parametric Activation: Unifying and Generalising Activation Functions Across Taskscited by 6
  5. 2023Language-conditioned Detection Transformercited by 5
  6. 2024Rectify the Regression Bias in Long-Tailed Object Detectioncited by 5
  7. 2024Fractal Calibration for long-tailed object detectioncited by 5
  8. 2024VLMine: Long-Tail Data Mining with Vision Language Modelscited by 4
  9. 2024Learning De-Biased Representations for Remote-Sensing Imagerycited by 4
  10. 2025AD-Det: Boosting Object Detection in UAV Images with Focused Small Objects and Balanced Tail Classescited by 2
  11. 2023Data-Centric Long-Tailed Image Recognitioncited by 1
  12. 2024Long-Tailed Object Detection Pre-training: Dynamic Rebalancing Contrastive Learning with Dual Reconstructioncited by 1
1 more
  1. 2026Information Density Imbalance in Visual Object Detectioncited by 0