# Long-Tailed Recognition Using Class-Balanced Experts

arXiv: https://arxiv.org/abs/2004.03706 · HTML: https://mlsanity.com/paper/2004.03706/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Apr 2020.

## Built on by (most cited first, 10 of 10)

- [ResLT: Residual Learning for Long-tailed Recognition](https://mlsanity.com/paper/2101.10633/) (2021)
- [Self-Supervised Aggregation of Diverse Experts for Test-Agnostic Long-Tailed Recognition](https://mlsanity.com/paper/2107.09249/) (2021)
- [DeepSMOTE: Fusing Deep Learning and SMOTE for Imbalanced Data](https://mlsanity.com/paper/2105.02340/) (2021)
- [GistNet: a Geometric Structure Transfer Network for Long-Tailed Recognition](https://mlsanity.com/paper/2105.00131/) (2021)
- [Teacher's pet: understanding and mitigating biases in distillation](https://mlsanity.com/paper/2106.10494/) (2021)
- [Balanced Product of Calibrated Experts for Long-Tailed Recognition](https://mlsanity.com/paper/2206.05260/) (2022)
- [Breadcrumbs: Adversarial Class-Balanced Sampling for Long-tailed Recognition](https://mlsanity.com/paper/2105.00127/) (2021)
- [Learning Prototype Classifiers for Long-Tailed Recognition](https://mlsanity.com/paper/2302.00491/) (2023)
- [Investigate the Essence of Long-Tailed Recognition from a Unified Perspective](https://mlsanity.com/paper/2107.03758/) (2021)
- [DRDF: Determining the Importance of Different Multimodal Information with Dual-Router Dynamic Framework](https://mlsanity.com/paper/2107.09909/) (2021)

## Abstract (arXiv)

Deep learning enables impressive performance in image recognition using large-scale artificially-balanced datasets. However, real-world datasets exhibit highly class-imbalanced distributions, yielding two main challenges: relative imbalance amongst the classes and data scarcity for mediumshot or fewshot classes. In this work, we address the problem of long-tailed recognition wherein the training set is highly imbalanced and the test set is kept balanced. Differently from existing paradigms relying on data-resampling, cost-sensitive learning, online hard example mining, loss objective reshaping, and/or memory-based modeling, we propose an ensemble of class-balanced experts that combines the strength of diverse classifiers. Our ensemble of class-balanced experts reaches results close to state-of-the-art and an extended ensemble establishes a new state-of-the-art on two benchmarks for long-tailed recognition. We conduct extensive experiments to analyse the performance of the ensembles, and discover that in modern large-scale datasets, relative imbalance is a harder problem than data scarcity. The training and evaluation code is available at https://github.com/ssfootball04/class-balanced-experts.