mlsanityData to 7 Oct 2026

Inverse Image Frequency for Long-tailed Image Recognition

arXiv 2209.04861 ↗First posted 11 Sep 2022cs.CVcited by 6

Not on the map. Why?

Abstract (arXiv)

The long-tailed distribution is a common phenomenon in the real world. Extracted large scale image datasets inevitably demonstrate the long-tailed property and models trained with imbalanced data can obtain high performance for the over-represented categories, but struggle for the under-represented categories, leading to biased predictions and performance degradation. To address this challenge, we propose a novel de-biasing method named Inverse Image Frequency (IIF). IIF is a multiplicative margin adjustment transformation of the logits in the classification layer of a convolutional neural network. Our method achieves stronger performance than similar works and it is especially useful for downstream tasks such as long-tailed instance segmentation as it produces fewer false positive detections. Our extensive experiments show that IIF surpasses the state of the art on many long-tailed benchmarks such as ImageNet-LT, CIFAR-LT, Places-LT and LVIS, reaching 55.8% top-1 accuracy with ResNet50 on ImageNet-LT and 26.2% segmentation AP with MaskRCNN on LVIS. Code available at https://github.com/kostas1515/iif

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 73 of its 96 references that are in the map. First posted on arXiv 11 Sep 2022.

Builds on

73 of 96 references.

References · 73

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  4. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  5. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  6. 2017Mask R-CNNcited by 7,259
  7. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
  8. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
  9. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  10. 2017Squeeze-and-Excitation Networkscited by 4,763
  11. 2015SSD: Single Shot MultiBox Detectorcited by 3,125
  12. 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,875
38 more
  1. 2018YOLOv3: An Incremental Improvementcited by 2,652
  2. 2016Aggregated Residual Transformations for Deep Neural Networkscited by 2,540
  3. 2019RandAugment: Practical automated data augmentation with a reduced search spacecited by 2,261
  4. 2019MMDetection: Open MMLab Detection Toolbox and Benchmarkcited by 1,379
  5. 2019Class-Balanced Loss Based on Effective Number of Samplescited by 1,239
  6. 2019LVIS: A Dataset for Large Vocabulary Instance Segmentationcited by 1,215
  7. 2019Learning Imbalanced Datasets with Label-Distribution-Aware Margin Losscited by 987
  8. 2019Decoupling Representation and Classifier for Long-Tailed Recognitioncited by 806
  9. 2019Large-Scale Long-Tailed Recognition in an Open Worldcited by 704
  10. 2020Long-tail learning via logit adjustmentcited by 605
  11. 2018Exploring the Limits of Weakly Supervised Pretrainingcited by 604
  12. 2019Hybrid Task Cascade for Instance Segmentationcited by 479
  13. 2019Distance-IoU Loss: Faster and Better Learning for Bounding Box Regressioncited by 454
  14. 2019Cascade R-CNN: High Quality Object Detection and Instance Segmentationcited by 428
  15. 2019BBN: Bilateral-Branch Network with Cumulative Learning for Long-Tailed Visual Recognitioncited by 403
  16. 2020Balanced Meta-Softmax for Long-Tailed Visual Recognitioncited by 397
  17. 2021ResNet strikes back: An improved training procedure in timmcited by 365
  18. 2018Detecting and Correcting for Label Shift with Black Box Predictorscited by 364
  19. 2020Equalization Loss for Long-Tailed Object Recognitioncited by 285
  20. 2020Long-tailed Recognition by Routing Diverse Distribution-Aware Expertscited by 270
  21. 2020Long-Tailed Classification by Keeping the Good and Removing the Bad Momentum Causal Effectcited by 256
  22. 2020DetectoRS: Detecting Objects with Recursive Feature Pyramid and Switchable Atrous Convolutioncited by 222
  23. 2021Improving Calibration for Long-Tailed Recognitioncited by 212
  24. 2021Distribution Alignment: A Unified Framework for Long-tail Visual Recognitioncited by 198
  25. 2020Disentangling Label Distribution for Long-tailed Visual Recognitioncited by 172
  26. 2015Cost Sensitive Learning of Deep Feature Representations from Imbalanced Datacited by 167
  27. 2020Overcoming Classifier Imbalance for Long-tail Object Detection with Balanced Group Softmaxcited by 152
  28. 2020Seesaw Loss for Long-Tailed Instance Segmentationcited by 146
  29. 2020Rethinking Class-Balanced Methods for Long-Tailed Visual Recognition from a Domain Adaptation Perspectivecited by 143
  30. 2021Contrastive Learning based Hybrid Networks for Long-Tailed Image Classificationcited by 130
  31. 2019Imbalance Problems in Object Detection: A Reviewcited by 118
  32. 2015Relay Backpropagation for Effective Learning of Deep Convolutional Neural Networkscited by 115
  33. 2020TIDE: A General Toolbox for Identifying Object Detection Errorscited by 113
  34. 2020The Devil is in Classification: A Simple Framework for Long-tail Object Detection and Instance Segmentationcited by 108
  35. 2022Long-Tailed Recognition via Weight Balancingcited by 107
  36. 2021The Majority Can Help The Minority: Context-rich Minority Oversampling for Long-tailed Classificationcited by 100
  37. 2020Equalization Loss v2: A New Gradient Balance Approach for Long-tailed Object Detectioncited by 99
  38. 2020Delving Deep into Label Smoothingcited by 94

50 most cited of 73 All 73 (JSON)

Built on by

Cited by year

Citing papers per year: 2024: 4; 2025: 2.

6 papers.

  1. 2024Enhanced Long-Tailed Recognition with Contrastive CutMix Augmentationcited by 6
  2. 2024Adaptive Parametric Activation: Unifying and Generalising Activation Functions Across Taskscited by 6
  3. 2024Fractal Calibration for long-tailed object detectioncited by 5
  4. 2025Dual-View Alignment Learning with Hierarchical-Prompt for Class-Imbalance Multi-Label Classificationcited by 2
  5. 2024Multiplicative Logit Adjustment Approximates Neural-Collapse-Aware Decision Boundary Adjustmentcited by 1
  6. 2025Normalizing Batch Normalization for Long-Tailed Recognitioncited by 0