# Balanced Sharpness-Aware Minimization for Imbalanced Regression

arXiv: https://arxiv.org/abs/2508.16973 · HTML: https://mlsanity.com/paper/2508.16973/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 41 references that are in the map.
- First posted on arXiv 23 Aug 2025.

## Builds on (most cited first, 28 of 28)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Sharpness-Aware Minimization for Efficiently Improving Generalization](https://mlsanity.com/paper/2010.01412/) (2020)
- [On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima](https://mlsanity.com/paper/1609.04836/) (2016)
- [Depth Map Prediction from a Single Image using a Multi-Scale Deep Network](https://mlsanity.com/paper/1406.2283/) (2014)
- [Visualizing the Loss Landscape of Neural Nets](https://mlsanity.com/paper/1712.09913/) (2017)
- [Deep Ordinal Regression Network for Monocular Depth Estimation](https://mlsanity.com/paper/1806.02446/) (2018)
- [Fantastic Generalization Measures and Where to Find Them](https://mlsanity.com/paper/1912.02178/) (2019)
- [SWAD: Domain Generalization by Seeking Flat Minima](https://mlsanity.com/paper/2102.08604/) (2021)
- [A simple yet effective baseline for 3d human pose estimation](https://mlsanity.com/paper/1705.03098/) (2017)
- [Entropy-SGD: Biasing Gradient Descent Into Wide Valleys](https://mlsanity.com/paper/1611.01838/) (2016)
- [Delving into Deep Imbalanced Regression](https://mlsanity.com/paper/2102.09554/) (2021)
- [Revisiting Single Image Depth Estimation: Toward Higher Resolution Maps with Accurate Object Boundaries](https://mlsanity.com/paper/1803.08673/) (2018)
- [Rich Human Feedback for Text-to-Image Generation](https://mlsanity.com/paper/2312.10240/) (2023)
- [Human Pose Regression with Residual Log-likelihood Estimation](https://mlsanity.com/paper/2107.11291/) (2021)
- [Joint Training of a Convolutional Network and a Graphical Model for Human Pose Estimation](https://mlsanity.com/paper/1406.2984/) (2014)
- [Sharpness-Aware Minimization Improves Language Model Generalization](https://mlsanity.com/paper/2110.08529/) (2021)
- [Tilted Empirical Risk Minimization](https://mlsanity.com/paper/2007.01162/) (2020)
- [Balanced MSE for Imbalanced Visual Regression](https://mlsanity.com/paper/2203.16427/) (2022)
- [A Closer Look at Smoothness in Domain Adversarial Training](https://mlsanity.com/paper/2206.08213/) (2022)
- [Rank-N-Contrast: Learning Continuous Representations for Regression](https://mlsanity.com/paper/2210.01189/) (2022)
- [RankSim: Ranking Similarity Regularization for Deep Imbalanced Regression](https://mlsanity.com/paper/2205.15236/) (2022)
- [Human pose estimation via Convolutional Part Heatmap Regression](https://mlsanity.com/paper/1609.01743/) (2016)
- [Improving Deep Regression with Ordinal Entropy](https://mlsanity.com/paper/2301.08915/) (2023)
- [ImbSAM: A Closer Look at Sharpness-Aware Minimization in Class-Imbalanced Recognition](https://mlsanity.com/paper/2308.07815/) (2023)
- [ConR: Contrastive Regularizer for Deep Imbalanced Regression](https://mlsanity.com/paper/2309.06651/) (2023)
- [A step towards understanding why classification helps regression](https://mlsanity.com/paper/2308.10603/) (2023)
- [Deep Imbalanced Regression via Hierarchical Classification Adjustment](https://mlsanity.com/paper/2310.17154/) (2023)
- [Label Encoding for Regression Networks](https://mlsanity.com/paper/2212.01927/) (2022)

## Built on by (most cited first, 1 of 1)

- [NCSAM Noise-Compensated Sharpness-Aware Minimization for Noisy Label Learning](https://mlsanity.com/paper/2601.19947/) (2026)

## Abstract (arXiv)

Regression is fundamental in computer vision and is widely used in various tasks including age estimation, depth estimation, target localization, etc However, real-world data often exhibits imbalanced distribution, making regression models perform poorly especially for target values with rare observations~(known as the imbalanced regression problem). In this paper, we reframe imbalanced regression as an imbalanced generalization problem. To tackle that, we look into the loss sharpness property for measuring the generalization ability of regression models in the observation space. Namely, given a certain perturbation on the model parameters, we check how model performance changes according to the loss values of different target observations. We propose a simple yet effective approach called Balanced Sharpness-Aware Minimization~(BSAM) to enforce the uniform generalization ability of regression models for the entire observation space. In particular, we start from the traditional sharpness-aware minimization and then introduce a novel targeted reweighting strategy to homogenize the generalization ability across the observation space, which guarantees a theoretical generalization bound. Extensive experiments on multiple vision regression tasks, including age and depth estimation, demonstrate that our BSAM method consistently outperforms existing approaches. The code is available hrefhttps://github.com/manmanjun/BSAMforImbalancedRegressionhere.