# A Strong Balanced-Softmax Classifier-Retraining Baseline for Long-Tailed Recognition

arXiv: https://arxiv.org/abs/2607.09832 · HTML: https://mlsanity.com/paper/2607.09832/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 29 of its 43 references that are in the map.
- First posted on arXiv 10 Jul 2026.

## Builds on (most cited first, 29 of 29)

- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [Supervised Contrastive Learning](https://mlsanity.com/paper/2004.11362/) (2020)
- [Class-Balanced Loss Based on Effective Number of Samples](https://mlsanity.com/paper/1901.05555/) (2019)
- [Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss](https://mlsanity.com/paper/1906.07413/) (2019)
- [CosFace: Large Margin Cosine Loss for Deep Face Recognition](https://mlsanity.com/paper/1801.09414/) (2018)
- [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)
- [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)
- [Long-tailed Recognition by Routing Diverse Distribution-Aware Experts](https://mlsanity.com/paper/2010.01809/) (2020)
- [Long-Tailed Classification by Keeping the Good and Removing the Bad Momentum Causal Effect](https://mlsanity.com/paper/2009.12991/) (2020)
- [NormFace: L2 Hypersphere Embedding for Face Verification](https://mlsanity.com/paper/1704.06369/) (2017)
- [Parametric Contrastive Learning](https://mlsanity.com/paper/2107.12028/) (2021)
- [Improving Calibration for Long-Tailed Recognition](https://mlsanity.com/paper/2104.00466/) (2021)
- [Disentangling Label Distribution for Long-tailed Visual Recognition](https://mlsanity.com/paper/2012.00321/) (2020)
- [Balanced Contrastive Learning for Long-Tailed Visual Recognition](https://mlsanity.com/paper/2207.09052/) (2022)
- [Contrastive Learning based Hybrid Networks for Long-Tailed Image Classification](https://mlsanity.com/paper/2103.14267/) (2021)
- [Deep Representation Learning on Long-tailed Data: A Learnable Embedding Augmentation Perspective](https://mlsanity.com/paper/2002.10826/) (2020)
- [MetaSAug: Meta Semantic Augmentation for Long-Tailed Visual Recognition](https://mlsanity.com/paper/2103.12579/) (2021)
- [Distributional Robustness Loss for Long-tail Learning](https://mlsanity.com/paper/2104.03066/) (2021)
- [A Survey on Long-Tailed Visual Recognition](https://mlsanity.com/paper/2205.13775/) (2022)
- [Long-tailed Visual Recognition via Gaussian Clouded Logit Adjustment](https://mlsanity.com/paper/2305.11733/) (2023)
- [Global and Local Mixture Consistency Cumulative Learning for Long-tailed Visual Recognitions](https://mlsanity.com/paper/2305.08661/) (2023)
- [Decoupled Contrastive Learning for Long-Tailed Recognition](https://mlsanity.com/paper/2403.06151/) (2024)
- [Decision Boundary-aware Generation for Long-tailed Learning](https://mlsanity.com/paper/2605.01468/) (2026)

## Abstract (arXiv)

Long-tailed recognition methods often modify losses, margins, or representations to reduce the dominance of frequent classes. We ask whether, after Balanced Softmax training, the remaining tail error can be reduced by retraining only the classifier. We evaluate BS-cRT, a two-stage procedure that trains a backbone and cosine classifier with Balanced Softmax, freezes the backbone, and updates only the classifier on balanced episodic batches. The second stage keeps the empirical-prior Balanced Softmax objective and uses raw cosine logits at inference. Across CIFAR-100-LT, CIFAR-10-LT, ImageNet-LT, and Places-LT, this classifier-only step consistently improves Few-shot accuracy over the matched Balanced Softmax checkpoint. At imbalance factor 100, Few-shot gains are +5.15 points on CIFAR-100-LT and +5.83 on CIFAR-10-LT; on ImageNet-LT and Places-LT, gains are +6.92 and +9.78 points, respectively, with a Top-1/Few-shot trade-off on ImageNet-LT. We also analyze Counterfactual Boundary Risk Minimization (CBRM), a boundary-probe extension using prototype-based features near decision boundaries. CBRM identifies two failure modes: scaled-logit cosine margins destabilize training, and corrected hardest-negative probes remain head-class anchored. The results support BS-cRT as a practical classifier-side baseline and indicate that boundary supervision must account for class frequency.