# Constructing Balance from Imbalance for Long-tailed Image Recognition

arXiv: https://arxiv.org/abs/2208.02567 · HTML: https://mlsanity.com/paper/2208.02567/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- Builds on 51 of its 71 references that are in the map.
- First posted on arXiv 4 Aug 2022.

## Builds on (most cited first, 30 of 51)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [RandAugment: Practical automated data augmentation with a reduced search space](https://mlsanity.com/paper/1909.13719/) (2019)
- [Variational Inference with Normalizing Flows](https://mlsanity.com/paper/1505.05770/) (2015)
- [Density estimation using Real NVP](https://mlsanity.com/paper/1605.08803/) (2016)
- [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)
- [Masked Autoregressive Flow for Density Estimation](https://mlsanity.com/paper/1705.07057/) (2017)
- [Improving Variational Inference with Inverse Autoregressive Flow](https://mlsanity.com/paper/1606.04934/) (2016)
- [Long-tail learning via logit adjustment](https://mlsanity.com/paper/2007.07314/) (2020)
- [A systematic study of the class imbalance problem in convolutional neural networks](https://mlsanity.com/paper/1710.05381/) (2017)
- [BBN: Bilateral-Branch Network with Cumulative Learning for Long-Tailed Visual Recognition](https://mlsanity.com/paper/1912.02413/) (2019)
- [Balanced Meta-Softmax for Long-Tailed Visual Recognition](https://mlsanity.com/paper/2007.10740/) (2020)
- [Dynamic Few-Shot Visual Learning without Forgetting](https://mlsanity.com/paper/1804.09458/) (2018)
- [Long-tailed Recognition by Routing Diverse Distribution-Aware Experts](https://mlsanity.com/paper/2010.01809/) (2020)
- [What is the Effect of Importance Weighting in Deep Learning?](https://mlsanity.com/paper/1812.03372/) (2018)
- [Parametric Contrastive Learning](https://mlsanity.com/paper/2107.12028/) (2021)
- [Rethinking the Value of Labels for Improving Class-Imbalanced Learning](https://mlsanity.com/paper/2006.07529/) (2020)
- [Improving Calibration for Long-Tailed Recognition](https://mlsanity.com/paper/2104.00466/) (2021)
- [Distribution Alignment: A Unified Framework for Long-tail Visual Recognition](https://mlsanity.com/paper/2103.16370/) (2021)
- [Learning From Multiple Experts: Self-paced Knowledge Distillation for Long-tailed Classification](https://mlsanity.com/paper/2001.01536/) (2020)
- [Disentangling Label Distribution for Long-tailed Visual Recognition](https://mlsanity.com/paper/2012.00321/) (2020)
- [Remix: Rebalanced Mixup](https://mlsanity.com/paper/2007.03943/) (2020)
- [Rethinking Class-Balanced Methods for Long-Tailed Visual Recognition from a Domain Adaptation Perspective](https://mlsanity.com/paper/2003.10780/) (2020)

## Built on by (most cited first, 25 of 25)

- [LPT: Long-tailed Prompt Tuning for Image Classification](https://mlsanity.com/paper/2210.01033/) (2022)
- [Learning Imbalanced Data with Vision Transformers](https://mlsanity.com/paper/2212.02015/) (2022)
- [A Systematic Review on Long-Tailed Learning](https://mlsanity.com/paper/2408.00483/) (2024)
- [MDCS: More Diverse Experts with Consistency Self-distillation for Long-tailed Recognition](https://mlsanity.com/paper/2308.09922/) (2023)
- [Symbol-LLM: Leverage Language Models for Symbolic System in Visual Human Activity Reasoning](https://mlsanity.com/paper/2311.17365/) (2023)
- [Meta-Causal Feature Learning for Out-of-Distribution Generalization](https://mlsanity.com/paper/2208.10156/) (2022)
- [Beyond Object Recognition: A New Benchmark towards Object Concept Learning](https://mlsanity.com/paper/2212.02710/) (2022)
- [A Comprehensive Survey on Imbalanced Data Learning](https://mlsanity.com/paper/2502.08960/) (2025)
- [Class-level Structural Relation Modelling and Smoothing for Visual Representation Learning](https://mlsanity.com/paper/2308.04142/) (2023)
- [Deep Imbalanced Regression via Hierarchical Classification Adjustment](https://mlsanity.com/paper/2310.17154/) (2023)
- [Distill Gold from Massive Ores: Bi-level Data Pruning towards Efficient Dataset Distillation](https://mlsanity.com/paper/2305.18381/) (2023)
- [GeNIe: Generative Hard Negative Images Through Diffusion](https://mlsanity.com/paper/2312.02548/) (2023)
- [VLM-KD: Knowledge Distillation from VLM for Long-Tail Visual Recognition](https://mlsanity.com/paper/2408.16930/) (2024)
- [A Square Peg in a Square Hole: Meta-Expert for Long-Tailed Semi-Supervised Learning](https://mlsanity.com/paper/2505.16341/) (2025)
- [SUG: Single-dataset Unified Generalization for 3D Point Cloud Classification](https://mlsanity.com/paper/2305.09160/) (2023)
- [LTRL: Boosting Long-tail Recognition via Reflective Learning](https://mlsanity.com/paper/2407.12568/) (2024)
- [Accurately Predicting Probabilities of Safety-Critical Rare Events for Intelligent Systems](https://mlsanity.com/paper/2403.13869/) (2024)
- [Generative Data Mining with Longtail-Guided Diffusion](https://mlsanity.com/paper/2502.01980/) (2025)
- [Graph Cuts with Arbitrary Size Constraints Through Optimal Transport](https://mlsanity.com/paper/2402.04732/) (2024)
- [Gradient-Aware Logit Adjustment Loss for Long-tailed Classifier](https://mlsanity.com/paper/2403.09036/) (2024)
- [IMWA: Iterative Model Weight Averaging Benefits Class-Imbalanced Learning Tasks](https://mlsanity.com/paper/2404.16331/) (2024)
- [From Uncertainty to Clarity: Uncertainty-Guided Class-Incremental Learning for Limited Biomedical Samples via Semantic Expansion](https://mlsanity.com/paper/2409.07757/) (2024)
- [Class Instance Balanced Learning for Long-Tailed Classification](https://mlsanity.com/paper/2307.05322/) (2023)
- [Training Over a Distribution of Hyperparameters for Enhanced Performance and Adaptability on Imbalanced Classification](https://mlsanity.com/paper/2410.03588/) (2024)
- [Vision Transformers versus convolutional neural networks for fine-grained orchid genus identification in a species-rich, data-poor flora: a controlled benchmark on the Orchidaceae of New Guinea](https://mlsanity.com/paper/2609.24064/) (2026)

## Abstract (arXiv)

Long-tailed image recognition presents massive challenges to deep learning systems since the imbalance between majority (head) classes and minority (tail) classes severely skews the data-driven deep neural networks. Previous methods tackle with data imbalance from the viewpoints of data distribution, feature space, and model design, etc. In this work, instead of directly learning a recognition model, we suggest confronting the bottleneck of head-to-tail bias before classifier learning, from the previously omitted perspective of balancing label space. To alleviate the head-to-tail bias, we propose a concise paradigm by progressively adjusting label space and dividing the head classes and tail classes, dynamically constructing balance from imbalance to facilitate the classification. With flexible data filtering and label space mapping, we can easily embed our approach to most classification models, especially the decoupled training methods. Besides, we find the separability of head-tail classes varies among different features with different inductive biases. Hence, our proposed model also provides a feature evaluation method and paves the way for long-tailed feature learning. Extensive experiments show that our method can boost the performance of state-of-the-arts of different types on widely-used benchmarks. Code is available at https://github.com/silicx/DLSA.