mlsanityData to 7 Oct 2026

Adaptive Class Suppression Loss for Long-Tail Object Detection

arXiv 2104.00885 ↗First posted 2 Apr 2021cs.CVcited by 55

Not on the map. Why?

Abstract (arXiv)

To address the problem of long-tail distribution for the large vocabulary object detection task, existing methods usually divide the whole categories into several groups and treat each group with different strategies. These methods bring the following two problems. One is the training inconsistency between adjacent categories of similar sizes, and the other is that the learned model is lack of discrimination for tail categories which are semantically similar to some of the head categories. In this paper, we devise a novel Adaptive Class Suppression Loss (ACSL) to effectively tackle the above problems and improve the detection performance of tail categories. Specifically, we introduce a statistic-free perspective to analyze the long-tail distribution, breaking the limitation of manual grouping. According to this perspective, our ACSL adjusts the suppression gradients for each sample of each class adaptively, ensuring the training consistency and boosting the discrimination for rare categories. Extensive experiments on long-tail datasets LVIS and Open Images show that the our ACSL achieves 5.18% and 5.2% improvements with ResNet50-FPN, and sets a new state of the art. Code and models are available at https://github.com/CASIA-IVA-Lab/ACSL.

Key facts. Cited by 55 papers in the map (data through 7 Oct 2026). Builds on 28 of its 42 references that are in the map. First posted on arXiv 2 Apr 2021.

Builds on

28 of 42 references.

References · 28

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  2. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  3. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  4. 2015SSD: Single Shot MultiBox Detectorcited by 3,125
  5. 2015Fast R-CNNcited by 2,930
  6. 2019FCOS: Fully Convolutional One-Stage Object Detectioncited by 1,573
  7. 2019MMDetection: Open MMLab Detection Toolbox and Benchmarkcited by 1,379
  8. 2017Cascade R-CNN: Delving into High Quality Object Detectioncited by 1,275
  9. 2019Class-Balanced Loss Based on Effective Number of Samplescited by 1,239
  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
16 more
  1. 2018CornerNet: Detecting Objects as Paired Keypointscited by 763
  2. 2019CenterNet: Keypoint Triplets for Object Detectioncited by 654
  3. 2018Exploring the Limits of Weakly Supervised Pretrainingcited by 604
  4. 2016R-FCN: Object Detection via Region-based Fully Convolutional Networkscited by 414
  5. 2020Balanced Meta-Softmax for Long-Tailed Visual Recognitioncited by 397
  6. 2020Equalization Loss for Long-Tailed Object Recognitioncited by 285
  7. 2019RepPoints: Point Set Representation for Object Detectioncited by 264
  8. 2019Libra R-CNN: Towards Balanced Learning for Object Detectioncited by 255
  9. 2019Bottom-up Object Detection by Grouping Extreme and Center Pointscited by 156
  10. 2020Overcoming Classifier Imbalance for Long-tail Object Detection with Balanced Group Softmaxcited by 152
  11. 2018Bounding Box Regression with Uncertainty for Accurate Object Detectioncited by 143
  12. 2017Single-Shot Refinement Neural Network for Object Detectioncited by 129
  13. 2020The Devil is in Classification: A Simple Framework for Long-tail Object Detection and Instance Segmentationcited by 108
  14. 2019ThunderNet: Towards Real-time Generic Object Detectioncited by 42
  15. 2019Towards Accurate One-Stage Object Detection with AP-Losscited by 36
  16. 2019CornerNet-Lite: Efficient Keypoint Based Object Detectioncited by 24

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 2; 2022: 18; 2023: 17; 2024: 10; 2025: 5; 2026: 3.

55 papers.

Sort:

By area:

  1. 2021Deep Long-Tailed Learning: A Surveycited by 416
  2. 2023Towards Open Vocabulary Learning: A Surveycited by 165
  3. 2022A Survey on Long-Tailed Visual Recognitioncited by 75
  4. 2022Equalized Focal Loss for Dense Long-Tailed Object Detectioncited by 46
  5. 2022TAM: Topology-Aware Margin Loss for Class-Imbalanced Node Classificationcited by 41
  6. 2021On Model Calibration for Long-Tailed Object Detection and Instance Segmentationcited by 39
  7. 2023MosaicFusion: Diffusion Models as Data Augmenters for Large Vocabulary Instance Segmentationcited by 35
  8. 2022Fine-Grained Predicates Learning for Scene Graph Generationcited by 27
  9. 2024A Systematic Review on Long-Tailed Learningcited by 27
  10. 2022Delving into Semantic Scale Imbalancecited by 22
  11. 2022When Noisy Labels Meet Long Tail Dilemmas: A Representation Calibration Methodcited by 21
  12. 2023DiGeo: Discriminative Geometry-Aware Learning for Generalized Few-Shot Object Detectioncited by 21
38 more
  1. 2022Relieving Long-tailed Instance Segmentation via Pairwise Class Balancecited by 18
  2. 2022Cloud-Device Collaborative Adaptation to Continual Changing Environments in the Real-worldcited by 16
  3. 2022Adaptive Fine-Grained Predicates Learning for Scene Graph Generationcited by 14
  4. 2023Rethinking Semi-Supervised Imbalanced Node Classification from Bias-Variance Decompositioncited by 13
  5. 2022Long-tailed Instance Segmentation using Gumbel Optimized Losscited by 12
  6. 2022Semi-Supervised Temporal Action Detection with Proposal-Free Maskingcited by 10
  7. 2022Learning with Free Object Segments for Long-Tailed Instance Segmentationcited by 8
  8. 2022The Equalization Losses: Gradient-Driven Training for Long-tailed Object Recognitioncited by 8
  9. 2022Deep Learning based Computer Vision Methods for Complex Traffic Environments Perception: A Reviewcited by 7
  10. 2023Oriented object detection in optical remote sensing images using deep learning: a surveycited by 7
  11. 2023Adjusting Logit in Gaussian Form for Long-Tailed Visual Recognitioncited by 7
  12. 2023Zone Evaluation: Revealing Spatial Bias in Object Detectioncited by 7
  13. 2022Inverse Image Frequency for Long-tailed Image Recognitioncited by 6
  14. 2022Bridging Images and Videos: A Simple Learning Framework for Large Vocabulary Video Object Detectioncited by 6
  15. 2023Generalized Few-Shot 3D Object Detection of LiDAR Point Cloud for Autonomous Drivingcited by 6
  16. 2023Towards Heterogeneous Long-tailed Learning: Benchmarking, Metrics, and Toolboxcited by 6
  17. 2024Adaptive Parametric Activation: Unifying and Generalising Activation Functions Across Taskscited by 6
  18. 2025Generalized Semantic Contrastive Learning via Embedding Side Information for Few-Shot Object Detectioncited by 6
  19. 2023Balanced Classification: A Unified Framework for Long-Tailed Object Detectioncited by 5
  20. 2024Rectify the Regression Bias in Long-Tailed Object Detectioncited by 5
  21. 2024Training Class-Imbalanced Diffusion Model Via Overlap Optimizationcited by 5
  22. 2024Fractal Calibration for long-tailed object detectioncited by 5
  23. 2025LIFT+: Lightweight Fine-Tuning for Long-Tail Learningcited by 5
  24. 2023Boosting Long-tailed Object Detection via Step-wise Learning on Smooth-tail Datacited by 3
  25. 2023Semi-Supervised and Long-Tailed Object Detection with CascadeMatchcited by 2
  26. 2023Enlarged Large Margin Loss for Imbalanced Classificationcited by 2
  27. 2023DST-Det: Simple Dynamic Self-Training for Open-Vocabulary Object Detectioncited by 1
  28. 2023Non-Visible Light Data Synthesis and Application: A Case Study for Synthetic Aperture Radar Imagerycited by 1
  29. 2023Multi-modality Affinity Inference for Weakly Supervised 3D Semantic Segmentationcited by 1
  30. 2024Long-Tailed Object Detection Pre-training: Dynamic Rebalancing Contrastive Learning with Dual Reconstructioncited by 1
  31. 2024Prior2Posterior: Model Prior Correction for Long-Tailed Learningcited by 1
  32. 2025CLIMB-3D: Continual Learning for Imbalanced 3D Instance Segmentationcited by 1
  33. 2022Object Detection in Aerial Images: What Improves the Accuracy?cited by 0
  34. 2022Improving Long-tailed Object Detection with Image-Level Supervision by Multi-Task Collaborative Learningcited by 0
  35. 2023Towards Spatial Equilibrium Object Detectioncited by 0
  36. 2024Optimizing for ROC Curves on Class-Imbalanced Data by Training over a Family of Loss Functionscited by 0
  37. 2024Training Over a Distribution of Hyperparameters for Enhanced Performance and Adaptability on Imbalanced Classificationcited by 0
  38. 2024Dataset Awareness is not Enough: Implementing Sample-level Tail Encouragement in Long-tailed Self-supervised Learningcited by 0

50 most cited of 55 All 55 (JSON)