mlsanityData to 7 Oct 2026

FASA: Feature Augmentation and Sampling Adaptation for Long-Tailed Instance Segmentation

arXiv 2102.12867 ↗First posted 25 Feb 2021cs.CVcited by 76

Not on the map. Why?

Abstract (arXiv)

Recent methods for long-tailed instance segmentation still struggle on rare object classes with few training data. We propose a simple yet effective method, Feature Augmentation and Sampling Adaptation (FASA), that addresses the data scarcity issue by augmenting the feature space especially for rare classes. Both the Feature Augmentation (FA) and feature sampling components are adaptive to the actual training status -- FA is informed by the feature mean and variance of observed real samples from past iterations, and we sample the generated virtual features in a loss-adapted manner to avoid over-fitting. FASA does not require any elaborate loss design, and removes the need for inter-class transfer learning that often involves large cost and manually-defined head/tail class groups. We show FASA is a fast, generic method that can be easily plugged into standard or long-tailed segmentation frameworks, with consistent performance gains and little added cost. FASA is also applicable to other tasks like long-tailed classification with state-of-the-art performance.

Key facts. Cited by 76 papers in the map (data through 7 Oct 2026). Builds on 42 of its 54 references that are in the map. First posted on arXiv 25 Feb 2021.

Builds on

42 of 54 references.

References · 42

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  3. 2017Mask R-CNNcited by 7,259
  4. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  5. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  6. 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,875
  7. 2016Aggregated Residual Transformations for Deep Neural Networkscited by 2,540
  8. 2015Learning Deep Features for Discriminative Localizationcited by 2,430
  9. 2019MMDetection: Open MMLab Detection Toolbox and Benchmarkcited by 1,379
  10. 2019Self-training with Noisy Student improves ImageNet classificationcited by 1,304
  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
30 more
  1. 2019Learning Imbalanced Datasets with Label-Distribution-Aware Margin Losscited by 987
  2. 2018CosFace: Large Margin Cosine Loss for Deep Face Recognitioncited by 968
  3. 2019Decoupling Representation and Classifier for Long-Tailed Recognitioncited by 806
  4. 2019Large-Scale Long-Tailed Recognition in an Open Worldcited by 704
  5. 2020Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentationcited by 595
  6. 2016Training Region-based Object Detectors with Online Hard Example Miningcited by 577
  7. 2019Hybrid Task Cascade for Instance Segmentationcited by 479
  8. 2019Cascade R-CNN: High Quality Object Detection and Instance Segmentationcited by 428
  9. 2019BBN: Bilateral-Branch Network with Cumulative Learning for Long-Tailed Visual Recognitioncited by 403
  10. 2020Balanced Meta-Softmax for Long-Tailed Visual Recognitioncited by 397
  11. 2020Equalization Loss for Long-Tailed Object Recognitioncited by 285
  12. 2020Long-Tailed Classification by Keeping the Good and Removing the Bad Momentum Causal Effectcited by 256
  13. 2020Overcoming Classifier Imbalance for Long-tail Object Detection with Balanced Group Softmaxcited by 152
  14. 2020Seesaw Loss for Long-Tailed Instance Segmentationcited by 146
  15. 2020Feature Space Augmentation for Long-Tailed Datacited by 136
  16. 2020M2m: Imbalanced Classification via Major-to-minor Translationcited by 134
  17. 2020Deep Representation Learning on Long-tailed Data: A Learnable Embedding Augmentation Perspectivecited by 120
  18. 2020TIDE: A General Toolbox for Identifying Object Detection Errorscited by 113
  19. 2020The Devil is in Classification: A Simple Framework for Long-tail Object Detection and Instance Segmentationcited by 108
  20. 2019Implicit Semantic Data Augmentation for Deep Networkscited by 106
  21. 2020Equalization Loss v2: A New Gradient Balance Approach for Long-tailed Object Detectioncited by 99
  22. 2019InstaBoost: Boosting Instance Segmentation via Probability Map Guided Copy-Pastingcited by 95
  23. 2018Deep Imbalanced Learning for Face Recognition and Attribute Predictioncited by 90
  24. 2020On Feature Normalization and Data Augmentationcited by 71
  25. 2021Evaluating Large-Vocabulary Object Detectors: The Devil is in the Detailscited by 57
  26. 2020Learning to Segment the Tailcited by 54
  27. 2020Forest R-CNN: Large-Vocabulary Long-Tailed Object Detection and Instance Segmentationcited by 41
  28. 2019Addressing the Loss-Metric Mismatch with Adaptive Loss Alignmentcited by 33
  29. 2019Generative Modeling for Small-Data Object Detectioncited by 20
  30. 2020Memory-based Jitter: Improving Visual Recognition on Long-tailed Data with Diversity In Memorycited by 15

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 5; 2022: 16; 2023: 20; 2024: 23; 2025: 10; 2026: 2.

76 papers.

Sort:

By area:

  1. 2021Deep Long-Tailed Learning: A Surveycited by 416
  2. 2023Towards Open Vocabulary Learning: A Surveycited by 165
  3. 2021Self-Supervised Aggregation of Diverse Experts for Test-Agnostic Long-Tailed Recognitioncited by 95
  4. 2021ACE: Ally Complementary Experts for Solving Long-Tailed Recognition in One-Shotcited by 86
  5. 2022A Survey on Long-Tailed Visual Recognitioncited by 75
  6. 2022Federated Learning on Heterogeneous and Long-Tailed Data via Classifier Re-Training with Federated Featurescited by 63
  7. 2022X-Paste: Revisiting Scalable Copy-Paste for Instance Segmentation using CLIP and StableDiffusioncited by 49
  8. 2024Probabilistic Contrastive Learning for Long-Tailed Visual Recognitioncited by 42
  9. 2021On Model Calibration for Long-Tailed Object Detection and Instance Segmentationcited by 39
  10. 2023How Re-sampling Helps for Long-Tail Learning?cited by 36
  11. 2023MosaicFusion: Diffusion Models as Data Augmenters for Large Vocabulary Instance Segmentationcited by 35
  12. 2023Fill-Up: Balancing Long-Tailed Data with Generative Modelscited by 34
38 more
  1. 2022From Forks to Forceps: A New Framework for Instance Segmentation of Surgical Instrumentscited by 32
  2. 2024A Systematic Review on Long-Tailed Learningcited by 27
  3. 2023Balancing Logit Variation for Long-tailed Semantic Segmentationcited by 26
  4. 2022ProCo: Prototype-aware Contrastive Learning for Long-tailed Medical Image Classificationcited by 25
  5. 2023Long-Tailed Visual Recognition via Self-Heterogeneous Integration with Knowledge Excavationcited by 22
  6. 2022Improving the Intra-class Long-tail in 3D Detection via Rare Example Miningcited by 19
  7. 2024Delving into the Trajectory Long-tail Distribution for Muti-object Trackingcited by 18
  8. 2022Label-Noise Learning with Intrinsically Long-Tailed Datacited by 17
  9. 2023Fed-GraB: Federated Long-tailed Learning with Self-Adjusting Gradient Balancercited by 17
  10. 2024Improving Visual Prompt Tuning by Gaussian Neighborhood Minimization for Long-Tailed Visual Recognitioncited by 15
  11. 2024Latent-based Diffusion Model for Long-tailed Recognitioncited by 14
  12. 2023Dynamically Conservative Self-Driving Planner for Long-Tail Casescited by 13
  13. 2024Geometric Prior Guided Feature Representation Learning for Long-Tailed Classificationcited by 10
  14. 2023Predicting and Enhancing the Fairness of DNNs with the Curvature of Perceptual Manifoldscited by 9
  15. 2025No time to train! Training-Free Reference-Based Instance Segmentationcited by 9
  16. 2022Learning with Free Object Segments for Long-Tailed Instance Segmentationcited by 8
  17. 2023Robust Asymmetric Loss for Multi-Label Long-Tailed Learningcited by 8
  18. 2022On Distinctive Image Captioning via Comparing and Reweightingcited by 7
  19. 2023RAHNet: Retrieval Augmented Hybrid Network for Long-tailed Graph Classificationcited by 7
  20. 2024VLM-KD: Knowledge Distillation from VLM for Long-Tail Visual Recognitioncited by 7
  21. 2022Inverse Image Frequency for Long-tailed Image Recognitioncited by 6
  22. 2022Bridging Images and Videos: A Simple Learning Framework for Large Vocabulary Video Object Detectioncited by 6
  23. 2023Data Optimization in Deep Learning: A Surveycited by 6
  24. 2024Adaptive Parametric Activation: Unifying and Generalising Activation Functions Across Taskscited by 6
  25. 2025Generative Active Learning for Long-tail Trajectory Prediction via Controllable Diffusion Modelcited by 6
  26. 2022Understanding the Tricks of Deep Learning in Medical Image Segmentation: Challenges and Future Directionscited by 5
  27. 2022A Survey of Dataset Refinement for Problems in Computer Vision Datasetscited by 5
  28. 2023Balanced Classification: A Unified Framework for Long-Tailed Object Detectioncited by 5
  29. 2023Orthogonal Uncertainty Representation of Data Manifold for Robust Long-Tailed Learningcited by 5
  30. 2024Fractal Calibration for long-tailed object detectioncited by 5
  31. 2024Class Imbalance in Object Detection: An Experimental Diagnosis and Study of Mitigation Strategiescited by 4
  32. 2024FedLF: Adaptive Logit Adjustment and Feature Optimization in Federated Long-Tailed Learningcited by 4
  33. 2024SimLTD: Simple Supervised and Semi-Supervised Long-Tailed Object Detectioncited by 4
  34. 2023Integrating Local Real Data with Global Gradient Prototypes for Classifier Re-Balancing in Federated Long-Tailed Learningcited by 3
  35. 2024Promptable Representation Distribution Learning and Data Augmentation for Gigapixel Histopathology WSI Analysiscited by 3
  36. 2025Augment to Segment: Tackling Pixel-Level Imbalance in Wheat Disease and Pest Segmentationcited by 3
  37. 2022Long-Tailed Classification with Gradual Balanced Loss and Adaptive Feature Generationcited by 2
  38. 2023Semi-Supervised and Long-Tailed Object Detection with CascadeMatchcited by 2

50 most cited of 76 All 76 (JSON)