# Distribution-Balanced Loss for Multi-Label Classification in Long-Tailed Datasets

arXiv: https://arxiv.org/abs/2007.09654 · HTML: https://mlsanity.com/paper/2007.09654/

## Key facts

- Cited by 122 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Jul 2020.

## Built on by (most cited first, 30 of 122)

- [Deep Long-Tailed Learning: A Survey](https://mlsanity.com/paper/2110.04596/) (2021)
- [Query2Label: A Simple Transformer Way to Multi-Label Classification](https://mlsanity.com/paper/2107.10834/) (2021)
- [MetaSAug: Meta Semantic Augmentation for Long-Tailed Visual Recognition](https://mlsanity.com/paper/2103.12579/) (2021)
- [ML-Decoder: Scalable and Versatile Classification Head](https://mlsanity.com/paper/2111.12933/) (2021)
- [A Survey on Long-Tailed Visual Recognition](https://mlsanity.com/paper/2205.13775/) (2022)
- [Adaptive Methods for Real-World Domain Generalization](https://mlsanity.com/paper/2103.15796/) (2021)
- [Trustworthy Long-Tailed Classification](https://mlsanity.com/paper/2111.09030/) (2021)
- [Adversarial Robustness under Long-Tailed Distribution](https://mlsanity.com/paper/2104.02703/) (2021)
- [Large Loss Matters in Weakly Supervised Multi-Label Classification](https://mlsanity.com/paper/2206.03740/) (2022)
- [Robust Long-Tailed Learning under Label Noise](https://mlsanity.com/paper/2108.11569/) (2021)
- [VideoLT: Large-scale Long-tailed Video Recognition](https://mlsanity.com/paper/2105.02668/) (2021)
- [Balancing Methods for Multi-label Text Classification with Long-Tailed Class Distribution](https://mlsanity.com/paper/2109.04712/) (2021)
- [MAT-Agent: Adaptive Multi-Agent Training Optimization](https://mlsanity.com/paper/2510.17845/) (2025)
- [Learning Imbalanced Data with Vision Transformers](https://mlsanity.com/paper/2212.02015/) (2022)
- [FoodLMM: A Versatile Food Assistant using Large Multi-modal Model](https://mlsanity.com/paper/2312.14991/) (2023)
- [Class-Balanced Distillation for Long-Tailed Visual Recognition](https://mlsanity.com/paper/2104.05279/) (2021)
- [Relational Subsets Knowledge Distillation for Long-tailed Retinal Diseases Recognition](https://mlsanity.com/paper/2104.11057/) (2021)
- [MovieCuts: A New Dataset and Benchmark for Cut Type Recognition](https://mlsanity.com/paper/2109.05569/) (2021)
- [Multi-label Classification with Partial Annotations using Class-aware Selective Loss](https://mlsanity.com/paper/2110.10955/) (2021)
- [Delving into Semantic Scale Imbalance](https://mlsanity.com/paper/2212.14613/) (2022)
- [Open Long-Tailed Recognition in a Dynamic World](https://mlsanity.com/paper/2208.08349/) (2022)
- [A Survey of Methods for Addressing Class Imbalance in Deep-Learning Based Natural Language Processing](https://mlsanity.com/paper/2210.04675/) (2022)
- [TagCLIP: A Local-to-Global Framework to Enhance Open-Vocabulary Multi-Label Classification of CLIP Without Training](https://mlsanity.com/paper/2312.12828/) (2023)
- [SFC: Shared Feature Calibration in Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2401.11719/) (2024)
- [Relieving Long-tailed Instance Segmentation via Pairwise Class Balance](https://mlsanity.com/paper/2201.02784/) (2022)
- [Multi-label affordance mapping from egocentric vision](https://mlsanity.com/paper/2309.02120/) (2023)
- [Sewer-ML: A Multi-Label Sewer Defect Classification Dataset and Benchmark](https://mlsanity.com/paper/2103.10895/) (2021)
- [Learning in Imperfect Environment: Multi-Label Classification with Long-Tailed Distribution and Partial Labels](https://mlsanity.com/paper/2304.10539/) (2023)
- [Fed-GraB: Federated Long-tailed Learning with Self-Adjusting Gradient Balancer](https://mlsanity.com/paper/2310.07587/) (2023)
- [End-to-End Neuro-Symbolic Reinforcement Learning with Textual Explanations](https://mlsanity.com/paper/2403.12451/) (2024)

## Abstract (arXiv)

We present a new loss function called Distribution-Balanced Loss for the multi-label recognition problems that exhibit long-tailed class distributions. Compared to conventional single-label classification problem, multi-label recognition problems are often more challenging due to two significant issues, namely the co-occurrence of labels and the dominance of negative labels (when treated as multiple binary classification problems). The Distribution-Balanced Loss tackles these issues through two key modifications to the standard binary cross-entropy loss: 1) a new way to re-balance the weights that takes into account the impact caused by label co-occurrence, and 2) a negative tolerant regularization to mitigate the over-suppression of negative labels. Experiments on both Pascal VOC and COCO show that the models trained with this new loss function achieve significant performance gains over existing methods. Code and models are available at: https://github.com/wutong16/DistributionBalancedLoss .