mlsanityData to 7 Oct 2026

Exploring Classification Equilibrium in Long-Tailed Object Detection

arXiv 2108.07507 ↗First posted 17 Aug 2021cs.CVcited by 51

Not on the map. Why?

Abstract (arXiv)

The conventional detectors tend to make imbalanced classification and suffer performance drop, when the distribution of the training data is severely skewed. In this paper, we propose to use the mean classification score to indicate the classification accuracy for each category during training. Based on this indicator, we balance the classification via an Equilibrium Loss (EBL) and a Memory-augmented Feature Sampling (MFS) method. Specifically, EBL increases the intensity of the adjustment of the decision boundary for the weak classes by a designed score-guided loss margin between any two classes. On the other hand, MFS improves the frequency and accuracy of the adjustment of the decision boundary for the weak classes through over-sampling the instance features of those classes. Therefore, EBL and MFS work collaboratively for finding the classification equilibrium in long-tailed detection, and dramatically improve the performance of tail classes while maintaining or even improving the performance of head classes. We conduct experiments on LVIS using Mask R-CNN with various backbones including ResNet-50-FPN and ResNet-101-FPN to show the superiority of the proposed method. It improves the detection performance of tail classes by 15.6 AP, and outperforms the most recent long-tailed object detectors by more than 1 AP. Code is available at https://github.com/fcjian/LOCE.

Key facts. Cited by 51 papers in the map (data through 7 Oct 2026). Builds on 23 of its 29 references that are in the map. First posted on arXiv 17 Aug 2021.

Builds on

23 of 29 references.

References · 23

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  3. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  4. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
  5. 2017Mask R-CNNcited by 7,259
  6. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  7. 2020Improved Baselines with Momentum Contrastive Learningcited by 2,282
  8. 2019FCOS: Fully Convolutional One-Stage Object Detectioncited by 1,573
  9. 2019MMDetection: Open MMLab Detection Toolbox and Benchmarkcited by 1,379
  10. 2019LVIS: A Dataset for Large Vocabulary Instance Segmentationcited by 1,215
  11. 2019Learning Imbalanced Datasets with Label-Distribution-Aware Margin Losscited by 987
  12. 2019Decoupling Representation and Classifier for Long-Tailed Recognitioncited by 806
11 more
  1. 2020Long-tail learning via logit adjustmentcited by 605
  2. 2020Balanced Meta-Softmax for Long-Tailed Visual Recognitioncited by 397
  3. 2020Equalization Loss for Long-Tailed Object Recognitioncited by 285
  4. 2020Overcoming Classifier Imbalance for Long-tail Object Detection with Balanced Group Softmaxcited by 152
  5. 2020Seesaw Loss for Long-Tailed Instance Segmentationcited by 146
  6. 2019Cross-Batch Memory for Embedding Learningcited by 130
  7. 2020The Devil is in Classification: A Simple Framework for Long-tail Object Detection and Instance Segmentationcited by 108
  8. 2020Equalization Loss v2: A New Gradient Balance Approach for Long-tailed Object Detectioncited by 99
  9. 2020Forest R-CNN: Large-Vocabulary Long-Tailed Object Detection and Instance Segmentationcited by 41
  10. 2019Memory-Based Neighbourhood Embedding for Visual Recognitioncited by 16
  11. 2020Representation Sharing for Fast Object Detector Search and Beyondcited by 9

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 15; 2023: 13; 2024: 18; 2025: 1; 2026: 3.

51 papers.

Sort:

By area:

  1. 2022Objaverse: A Universe of Annotated 3D Objectscited by 1,522
  2. 2022Detecting Twenty-thousand Classes using Image-level Supervisioncited by 613
  3. 2021Deep Long-Tailed Learning: A Surveycited by 416
  4. 2022PromptDet: Towards Open-vocabulary Detection using Uncurated Imagescited by 133
  5. 2022Long-Tailed Recognition via Weight Balancingcited by 107
  6. 2022Equalized Focal Loss for Dense Long-Tailed Object Detectioncited by 46
  7. 2023ImbSAM: A Closer Look at Sharpness-Aware Minimization in Class-Imbalanced Recognitioncited by 31
  8. 2022Fine-Grained Predicates Learning for Scene Graph Generationcited by 27
  9. 2024A Systematic Review on Long-Tailed Learningcited by 27
  10. 2024InstaGen: Enhancing Object Detection by Training on Synthetic Datasetcited by 26
  11. 2022Delving into Semantic Scale Imbalancecited by 22
  12. 2022AeDet: Azimuth-invariant Multi-view 3D Object Detectioncited by 19
38 more
  1. 2022Relieving Long-tailed Instance Segmentation via Pairwise Class Balancecited by 18
  2. 2024Delving into the Trajectory Long-tail Distribution for Muti-object Trackingcited by 18
  3. 2023Long-Tailed Recognition by Mutual Information Maximization between Latent Features and Ground-Truth Labelscited by 16
  4. 2022Hierarchical Memory Learning for Fine-Grained Scene Graph Generationcited by 15
  5. 2022Adaptive Fine-Grained Predicates Learning for Scene Graph Generationcited by 14
  6. 2023Long-tail Detection with Effective Class-Marginscited by 13
  7. 2022Long-tailed Instance Segmentation using Gumbel Optimized Losscited by 12
  8. 2023Wrapped Cauchy Distributed Angular Softmax for Long-Tailed Visual Recognitioncited by 11
  9. 2024Open-Vocabulary Object Detection via Language Hierarchycited by 10
  10. 2022Logit Normalization for Long-tail Object Detectioncited by 8
  11. 2022Towards Generalized Few-Shot Open-Set Object Detectioncited by 8
  12. 2024Underwater Object Detection in the Era of Artificial Intelligence: Current, Challenge, and Futurecited by 8
  13. 2022Inverse Image Frequency for Long-tailed Image Recognitioncited by 6
  14. 2024Adaptive Parametric Activation: Unifying and Generalising Activation Functions Across Taskscited by 6
  15. 2023Balanced Classification: A Unified Framework for Long-Tailed Object Detectioncited by 5
  16. 2024Rectify the Regression Bias in Long-Tailed Object Detectioncited by 5
  17. 2024Fractal Calibration for long-tailed object detectioncited by 5
  18. 2024V-MIND: Building Versatile Monocular Indoor 3D Detector with Diverse 2D Annotationscited by 4
  19. 2023A Survey of Historical Learning: Learning Models with Learning Historycited by 3
  20. 2024Gradient-based Sampling for Class Imbalanced Semi-supervised Object Detectioncited by 3
  21. 2023Balanced Audiovisual Dataset for Imbalance Analysiscited by 2
  22. 2023Semi-Supervised and Long-Tailed Object Detection with CascadeMatchcited by 2
  23. 2023Informative Scene Graph Generation via Debiasingcited by 2
  24. 2024Domain Adaptation for Large-Vocabulary Object Detectorscited by 2
  25. 2023NP-Match: Towards a New Probabilistic Model for Semi-Supervised Learningcited by 1
  26. 2023AnoOnly: Semi-Supervised Anomaly Detection with the Only Loss on Anomaliescited by 1
  27. 2024Long-Tailed Object Detection Pre-training: Dynamic Rebalancing Contrastive Learning with Dual Reconstructioncited by 1
  28. 2025Divide, Weight, and Route: Difficulty-Aware Optimization with Dynamic Expert Fusion for Long-tailed Recognitioncited by 1
  29. 2026NetMamba+: A Framework of Pre-trained Models for Efficient and Accurate Network Traffic Classificationcited by 1
  30. 2023Propheter: Prophetic Teacher Guided Long-Tailed Distribution Learningcited by 0
  31. 2023On The Relationship Between Continual Learning and Long-Tailed Recognitioncited by 0
  32. 2024Optimizing for ROC Curves on Class-Imbalanced Data by Training over a Family of Loss Functionscited by 0
  33. 2024Rethinking Class-Incremental Learning from a Dynamic Imbalanced Learning Perspectivecited by 0
  34. 2024Holistic and Historical Instance Comparison for Cervical Cell Detectioncited by 0
  35. 2024Training Over a Distribution of Hyperparameters for Enhanced Performance and Adaptability on Imbalanced Classificationcited by 0
  36. 2024RICASSO: Reinforced Imbalance Learning with Class-Aware Self-Supervised Outliers Exposurecited by 0
  37. 2024Dataset Awareness is not Enough: Implementing Sample-level Tail Encouragement in Long-tailed Self-supervised Learningcited by 0
  38. 2026VMF-GOS: Geometry-guided virtual Outlier Synthesis for Long-Tailed OOD Detectioncited by 0

50 most cited of 51 All 51 (JSON)