mlsanityData to 14 Oct 2026

Image-Level or Object-Level? A Tale of Two Resampling Strategies for Long-Tailed Detection

arXiv 2104.05702 ↗First posted 12 Apr 2021cs.CV cs.LGcited by 27

Not on the map. Why?

Abstract (arXiv)

Training on datasets with long-tailed distributions has been challenging for major recognition tasks such as classification and detection. To deal with this challenge, image resampling is typically introduced as a simple but effective approach. However, we observe that long-tailed detection differs from classification since multiple classes may be present in one image. As a result, image resampling alone is not enough to yield a sufficiently balanced distribution at the object level. We address object-level resampling by introducing an object-centric memory replay strategy based on dynamic, episodic memory banks. Our proposed strategy has two benefits: 1) convenient object-level resampling without significant extra computation, and 2) implicit feature-level augmentation from model updates. We show that image-level and object-level resamplings are both important, and thus unify them with a joint resampling strategy (RIO). Our method outperforms state-of-the-art long-tailed detection and segmentation methods on LVIS v0.5 across various backbones. Code is available at https://github.com/NVlabs/RIO.

Key facts. Cited by 27 papers in the map (data through 14 Oct 2026). Builds on 25 of its 35 references that are in the map. First posted on arXiv 12 Apr 2021.

Builds on

25 of 35 references.

References · 25

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  2. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  3. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,513
  4. 2017Mask R-CNNcited by 7,277
  5. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
  6. 2017Prototypical Networks for Few-shot Learningcited by 3,015
  7. 2020Improved Baselines with Momentum Contrastive Learningcited by 2,287
  8. 2016Matching Networks for One Shot Learningcited by 2,255
  9. 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,054
  10. 2018Unsupervised Feature Learning via Non-Parametric Instance-level Discriminationcited by 1,845
  11. 2019Class-Balanced Loss Based on Effective Number of Samplescited by 1,245
  12. 2019LVIS: A Dataset for Large Vocabulary Instance Segmentationcited by 1,217
13 more
  1. 2019Learning Imbalanced Datasets with Label-Distribution-Aware Margin Losscited by 989
  2. 2019Decoupling Representation and Classifier for Long-Tailed Recognitioncited by 809
  3. 2019Large-Scale Long-Tailed Recognition in an Open Worldcited by 705
  4. 2019A Closer Look at Few-shot Classificationcited by 684
  5. 2018Exploring the Limits of Weakly Supervised Pretrainingcited by 605
  6. 2020Equalization Loss for Long-Tailed Object Recognitioncited by 285
  7. 2020Frustratingly Simple Few-Shot Object Detectioncited by 282
  8. 2018Low-Shot Learning from Imaginary Datacited by 181
  9. 2020Overcoming Classifier Imbalance for Long-tail Object Detection with Balanced Group Softmaxcited by 152
  10. 2020Seesaw Loss for Long-Tailed Instance Segmentationcited by 146
  11. 2015Relay Backpropagation for Effective Learning of Deep Convolutional Neural Networkscited by 115
  12. 2020Learning to Segment the Tailcited by 54
  13. 2020Forest R-CNN: Large-Vocabulary Long-Tailed Object Detection and Instance Segmentationcited by 41

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 2; 2022: 10; 2023: 4; 2024: 7; 2025: 2; 2026: 2.

27 papers.

Sort:

  1. 2022Detecting Twenty-thousand Classes using Image-level Supervisioncited by 614
  2. 2022RankSim: Ranking Similarity Regularization for Deep Imbalanced Regressioncited by 52
  3. 2022Discovering Objects that Can Movecited by 44
  4. 2021On Model Calibration for Long-Tailed Object Detection and Instance Segmentationcited by 39
  5. 2022BigDetection: A Large-scale Benchmark for Improved Object Detector Pre-trainingcited by 33
  6. 2024A Systematic Review on Long-Tailed Learningcited by 28
  7. 2021Taxonomy of Machine Learning Safety: A Survey and Primercited by 25
  8. 2022Open Vocabulary Object Detection with Proposal Mining and Prediction Equalizationcited by 23
  9. 2022Relieving Long-tailed Instance Segmentation via Pairwise Class Balancecited by 18
  10. 2024Trapped in texture bias? A large scale comparison of deep instance segmentationcited by 10
  11. 2024Continuous Contrastive Learning for Long-Tailed Semi-Supervised Recognitioncited by 10
  12. 2024Open-Vocabulary Object Detection via Language Hierarchycited by 10
15 more
  1. 2022Learning with Free Object Segments for Long-Tailed Instance Segmentationcited by 8
  2. 2024Underwater Object Detection in the Era of Artificial Intelligence: Current, Challenge, and Futurecited by 8
  3. 2023Instance-Aware Repeat Factor Sampling for Long-Tailed Object Detectioncited by 7
  4. 2022Bridging Images and Videos: A Simple Learning Framework for Large Vocabulary Video Object Detectioncited by 6
  5. 2025TAET: Two-Stage Adversarial Equalization Training on Long-Tailed Distributionscited by 6
  6. 2023Balanced Classification: A Unified Framework for Long-Tailed Object Detectioncited by 5
  7. 2022Cannot See the Forest for the Trees: Aggregating Multiple Viewpoints to Better Classify Objects in Videoscited by 2
  8. 2023Semi-Supervised and Long-Tailed Object Detection with CascadeMatchcited by 2
  9. 2023Ranking Regularization for Critical Rare Classes: Minimizing False Positives at a High True Positive Ratecited by 1
  10. 2024A Bilevel Optimization Framework for Imbalanced Data Classificationcited by 1
  11. 2026TMI: Text-to-Image Meets Image-to-Image for Complementary Data Synthesis to Boost Long-Tailed Instance Segmentationcited by 1
  12. 2022Improving Long-tailed Object Detection with Image-Level Supervision by Multi-Task Collaborative Learningcited by 0
  13. 2024Rethinking Class-Incremental Learning from a Dynamic Imbalanced Learning Perspectivecited by 0
  14. 2025Sampling Imbalanced Data with Multi-objective Bilevel Optimizationcited by 0
  15. 2026Information Density Imbalance in Visual Object Detectioncited by 0