# Class-Difficulty Based Methods for Long-Tailed Visual Recognition

arXiv: https://arxiv.org/abs/2207.14499 · HTML: https://mlsanity.com/paper/2207.14499/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 35 references that are in the map.
- First posted on arXiv 29 Jul 2022.

## Builds on (most cited first, 19 of 19)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Distributed Representations of Words and Phrases and their Compositionality](https://mlsanity.com/paper/1310.4546/) (2013)
- [The Kinetics Human Action Video Dataset](https://mlsanity.com/paper/1705.06950/) (2017)
- [Class-Balanced Loss Based on Effective Number of Samples](https://mlsanity.com/paper/1901.05555/) (2019)
- [LVIS: A Dataset for Large Vocabulary Instance Segmentation](https://mlsanity.com/paper/1908.03195/) (2019)
- [Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss](https://mlsanity.com/paper/1906.07413/) (2019)
- [Decoupling Representation and Classifier for Long-Tailed Recognition](https://mlsanity.com/paper/1910.09217/) (2019)
- [Large-Scale Long-Tailed Recognition in an Open World](https://mlsanity.com/paper/1904.05160/) (2019)
- [Learning to Reweight Examples for Robust Deep Learning](https://mlsanity.com/paper/1803.09050/) (2018)
- [Can Spatiotemporal 3D CNNs Retrace the History of 2D CNNs and ImageNet?](https://mlsanity.com/paper/1711.09577/) (2017)
- [Deep Metric Learning via Lifted Structured Feature Embedding](https://mlsanity.com/paper/1511.06452/) (2015)
- [Equalization Loss for Long-Tailed Object Recognition](https://mlsanity.com/paper/2003.05176/) (2020)
- [Overcoming Classifier Imbalance for Long-tail Object Detection with Balanced Group Softmax](https://mlsanity.com/paper/2006.10408/) (2020)
- [Rethinking Class-Balanced Methods for Long-Tailed Visual Recognition from a Domain Adaptation Perspective](https://mlsanity.com/paper/2003.10780/) (2020)
- [The Devil is in Classification: A Simple Framework for Long-tail Object Detection and Instance Segmentation](https://mlsanity.com/paper/2007.11978/) (2020)
- [Deep Imbalanced Learning for Face Recognition and Attribute Prediction](https://mlsanity.com/paper/1806.00194/) (2018)
- [Class-Wise Difficulty-Balanced Loss for Solving Class-Imbalance](https://mlsanity.com/paper/2010.01824/) (2020)
- [Classification Calibration for Long-tail Instance Segmentation](https://mlsanity.com/paper/1910.13081/) (2019)

## Built on by (most cited first, 23 of 23)

- [CUDA: Curriculum of Data Augmentation for Long-Tailed Recognition](https://mlsanity.com/paper/2302.05499/) (2023)
- [Use Your Head: Improving Long-Tail Video Recognition](https://mlsanity.com/paper/2304.01143/) (2023)
- [NCL++: Nested Collaborative Learning for Long-Tailed Visual Recognition](https://mlsanity.com/paper/2306.16709/) (2023)
- [Geometric Prior Guided Feature Representation Learning for Long-Tailed Classification](https://mlsanity.com/paper/2401.11436/) (2024)
- [Predicting and Enhancing the Fairness of DNNs with the Curvature of Perceptual Manifolds](https://mlsanity.com/paper/2303.12307/) (2023)
- [Adjusting Logit in Gaussian Form for Long-Tailed Visual Recognition](https://mlsanity.com/paper/2305.10648/) (2023)
- [DRoP: Distributionally Robust Data Pruning](https://mlsanity.com/paper/2404.05579/) (2024)
- [Dynamic Loss For Robust Learning](https://mlsanity.com/paper/2211.12506/) (2022)
- [Unveiling and Mitigating Generalized Biases of DNNs through the Intrinsic Dimensions of Perceptual Manifolds](https://mlsanity.com/paper/2404.13859/) (2024)
- [Orthogonal Uncertainty Representation of Data Manifold for Robust Long-Tailed Learning](https://mlsanity.com/paper/2310.10090/) (2023)
- [Curvature Learning for Generalization of Hyperbolic Neural Networks](https://mlsanity.com/paper/2508.17232/) (2025)
- [Difficulty-Net: Learning to Predict Difficulty for Long-Tailed Recognition](https://mlsanity.com/paper/2209.02960/) (2022)
- [Data-Centric Long-Tailed Image Recognition](https://mlsanity.com/paper/2311.01744/) (2023)
- [Noisy Ostracods: A Fine-Grained, Imbalanced Real-World Dataset for Benchmarking Robust Machine Learning and Label Correction Methods](https://mlsanity.com/paper/2412.02313/) (2024)
- [Compositional Attribute Imbalance in Vision Datasets](https://mlsanity.com/paper/2506.14418/) (2025)
- [Anisotropic Diffusion Probabilistic Model for Imbalanced Image Classification](https://mlsanity.com/paper/2409.14313/) (2024)
- [Reducing Class Bias In Data-Balanced Datasets Through Hardness-Based Resampling](https://mlsanity.com/paper/2504.07031/) (2025)
- [BOOST: Out-of-Distribution-Informed Adaptive Sampling for Bias Mitigation in Stylistic Convolutional Neural Networks](https://mlsanity.com/paper/2507.07134/) (2025)
- [Semantic-guided Fine-tuning of Foundation Model for Long-tailed Visual Recognition](https://mlsanity.com/paper/2507.12807/) (2025)
- [ART: Adaptive Resampling-based Training for Imbalanced Classification](https://mlsanity.com/paper/2509.00955/) (2025)
- [Optimizing Class Distributions for Bias-Aware Multi-Class Learning](https://mlsanity.com/paper/2509.11588/) (2025)
- [Information Density Imbalance in Visual Object Detection](https://mlsanity.com/paper/2609.02369/) (2026)
- [GA-EIRFS: A Geometry-Augmented Repeat-Factor Sampling Method for Long-Tailed LiDAR 3D Object Detection](https://mlsanity.com/paper/2609.38116/) (2026)

## Abstract (arXiv)

Long-tailed datasets are very frequently encountered in real-world use cases where few classes or categories (known as majority or head classes) have higher number of data samples compared to the other classes (known as minority or tail classes). Training deep neural networks on such datasets gives results biased towards the head classes. So far, researchers have come up with multiple weighted loss and data re-sampling techniques in efforts to reduce the bias. However, most of such techniques assume that the tail classes are always the most difficult classes to learn and therefore need more weightage or attention. Here, we argue that the assumption might not always hold true. Therefore, we propose a novel approach to dynamically measure the instantaneous difficulty of each class during the training phase of the model. Further, we use the difficulty measures of each class to design a novel weighted loss technique called `class-wise difficulty based weighted (CDB-W) loss' and a novel data sampling technique called `class-wise difficulty based sampling (CDB-S)'. To verify the wide-scale usability of our CDB methods, we conducted extensive experiments on multiple tasks such as image classification, object detection, instance segmentation and video-action classification. Results verified that CDB-W loss and CDB-S could achieve state-of-the-art results on many class-imbalanced datasets such as ImageNet-LT, LVIS and EGTEA, that resemble real-world use cases.