mlsanityData to 7 Oct 2026

DropLoss for Long-Tail Instance Segmentation

arXiv 2104.06402 ↗First posted 13 Apr 2021cs.CVcited by 32

Not on the map. Why?

Abstract (arXiv)

Long-tailed class distributions are prevalent among the practical applications of object detection and instance segmentation. Prior work in long-tail instance segmentation addresses the imbalance of losses between rare and frequent categories by reducing the penalty for a model incorrectly predicting a rare class label. We demonstrate that the rare categories are heavily suppressed by correct background predictions, which reduces the probability for all foreground categories with equal weight. Due to the relative infrequency of rare categories, this leads to an imbalance that biases towards predicting more frequent categories. Based on this insight, we develop DropLoss -- a novel adaptive loss to compensate for this imbalance without a trade-off between rare and frequent categories. With this loss, we show state-of-the-art mAP across rare, common, and frequent categories on the LVIS dataset.

Key facts. Cited by 32 papers in the map (data through 7 Oct 2026). Builds on 20 of its 37 references that are in the map. First posted on arXiv 13 Apr 2021.

Builds on

20 of 37 references.

References · 20

  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. 2017Mask R-CNNcited by 7,259
  4. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  5. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,829
  6. 2015SSD: Single Shot MultiBox Detectorcited by 3,125
  7. 2015Fast R-CNNcited by 2,930
  8. 2013Rich feature hierarchies for accurate object detection and semantic segmentationcited by 2,160
  9. 2016Identity Mappings in Deep Residual Networkscited by 1,960
  10. 2017Cascade R-CNN: Delving into High Quality Object Detectioncited by 1,275
  11. 2019Class-Balanced Loss Based on Effective Number of Samplescited by 1,239
  12. 2019LVIS: A Dataset for Large Vocabulary Instance Segmentationcited by 1,215
8 more
  1. 2019Learning Imbalanced Datasets with Label-Distribution-Aware Margin Losscited by 987
  2. 2019Decoupling Representation and Classifier for Long-Tailed Recognitioncited by 806
  3. 2019Large-Scale Long-Tailed Recognition in an Open Worldcited by 704
  4. 2018Exploring the Limits of Weakly Supervised Pretrainingcited by 604
  5. 2020Equalization Loss for Long-Tailed Object Recognitioncited by 285
  6. 2020Rethinking Class-Balanced Methods for Long-Tailed Visual Recognition from a Domain Adaptation Perspectivecited by 143
  7. 2018Gradient Harmonized Single-stage Detectorcited by 114
  8. 2016Range Loss for Deep Face Recognition with Long-tailcited by 111

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 2; 2022: 12; 2023: 5; 2024: 10; 2025: 1; 2026: 2.

32 papers.

Sort:

By area:

  1. 2021Deep Long-Tailed Learning: A Surveycited by 416
  2. 2022Language-Grounded Indoor 3D Semantic Segmentation in the Wildcited by 243
  3. 2022A Survey on Long-Tailed Visual Recognitioncited by 75
  4. 2021On Model Calibration for Long-Tailed Object Detection and Instance Segmentationcited by 39
  5. 2023FREDOM: Fairness Domain Adaptation Approach to Semantic Scene Understandingcited by 27
  6. 2022Delving into Semantic Scale Imbalancecited by 22
  7. 2022Improving the Intra-class Long-tail in 3D Detection via Rare Example Miningcited by 19
  8. 2022Relieving Long-tailed Instance Segmentation via Pairwise Class Balancecited by 18
  9. 2023Fairness Continual Learning Approach to Semantic Scene Understanding in Open-World Environmentscited by 16
  10. 2024Improving Visual Prompt Tuning by Gaussian Neighborhood Minimization for Long-Tailed Visual Recognitioncited by 15
  11. 2022Long-tailed Instance Segmentation using Gumbel Optimized Losscited by 12
  12. 2024Trapped in texture bias? A large scale comparison of deep instance segmentationcited by 10
20 more
  1. 2022Learning with Free Object Segments for Long-Tailed Instance Segmentationcited by 8
  2. 2022Inverse Image Frequency for Long-tailed Image Recognitioncited by 6
  3. 2022Bridging Images and Videos: A Simple Learning Framework for Large Vocabulary Video Object Detectioncited by 6
  4. 2024Adaptive Parametric Activation: Unifying and Generalising Activation Functions Across Taskscited by 6
  5. 2023Balanced Classification: A Unified Framework for Long-Tailed Object Detectioncited by 5
  6. 2024Rectify the Regression Bias in Long-Tailed Object Detectioncited by 5
  7. 2024Shap-Mix: Shapley Value Guided Mixing for Long-Tailed Skeleton Based Action Recognitioncited by 5
  8. 2024Fractal Calibration for long-tailed object detectioncited by 5
  9. 2022EM-Paste: EM-guided Cut-Paste with DALL-E Augmentation for Image-level Weakly Supervised Instance Segmentationcited by 4
  10. 2024VLMine: Long-Tail Data Mining with Vision Language Modelscited by 4
  11. 2022Instance Segmentation for Chinese Character Stroke Extraction, Datasets and Benchmarkscited by 3
  12. 2023Boosting Long-tailed Object Detection via Step-wise Learning on Smooth-tail Datacited by 3
  13. 2024Frequency-based Matcher for Long-tailed Semantic Segmentationcited by 3
  14. 2023CoMaL: Conditional Maximum Likelihood Approach to Self-supervised Domain Adaptation in Long-tail Semantic Segmentationcited by 2
  15. 2024Long-Tailed Object Detection Pre-training: Dynamic Rebalancing Contrastive Learning with Dual Reconstructioncited by 1
  16. 2024PAD-F: Prior-Aware Debiasing Framework for Long-Tailed X-ray Prohibited Item Detectioncited by 1
  17. 2022A Benchmark of Long-tailed Instance Segmentation with Noisy Labelscited by 0
  18. 2025Cost-Sensitive Learning for Long-Tailed Temporal Action Segmentationcited by 0
  19. 2026Neural Prior Estimation: Learning Class Priors from Latent Representationscited by 0
  20. 2026Information Density Imbalance in Visual Object Detectioncited by 0