# Striking the Right Balance with Uncertainty

arXiv: https://arxiv.org/abs/1901.07590 · HTML: https://mlsanity.com/paper/1901.07590/

## Key facts

- Cited by 79 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Jan 2019.

## Built on by (most cited first, 30 of 79)

- [Deep Long-Tailed Learning: A Survey](https://mlsanity.com/paper/2110.04596/) (2021)
- [Distribution Alignment: A Unified Framework for Long-tail Visual Recognition](https://mlsanity.com/paper/2103.16370/) (2021)
- [Targeted Supervised Contrastive Learning for Long-Tailed Recognition](https://mlsanity.com/paper/2111.13998/) (2021)
- [Long-Tailed Recognition via Weight Balancing](https://mlsanity.com/paper/2203.14197/) (2022)
- [Distributional Robustness Loss for Long-tail Learning](https://mlsanity.com/paper/2104.03066/) (2021)
- [Adversarial Robustness under Long-Tailed Distribution](https://mlsanity.com/paper/2104.02703/) (2021)
- [AutoBalance: Optimized Loss Functions for Imbalanced Data](https://mlsanity.com/paper/2201.01212/) (2022)
- [On Exposing the Challenging Long Tail in Future Prediction of Traffic Actors](https://mlsanity.com/paper/2103.12474/) (2021)
- [Orthogonal Projection Loss](https://mlsanity.com/paper/2103.14021/) (2021)
- [Crop mapping from image time series: deep learning with multi-scale label hierarchies](https://mlsanity.com/paper/2102.08820/) (2021)
- [Towards Long-Tailed 3D Detection](https://mlsanity.com/paper/2211.08691/) (2022)
- [Towards Calibrated Model for Long-Tailed Visual Recognition from Prior Perspective](https://mlsanity.com/paper/2111.03874/) (2021)
- [Analyzing Overfitting under Class Imbalance in Neural Networks for Image Segmentation](https://mlsanity.com/paper/2102.10365/) (2021)
- [Probabilistic Representations for Video Contrastive Learning](https://mlsanity.com/paper/2204.03946/) (2022)
- [Fill-Up: Balancing Long-Tailed Data with Generative Models](https://mlsanity.com/paper/2306.07200/) (2023)
- [Class-Balanced Distillation for Long-Tailed Visual Recognition](https://mlsanity.com/paper/2104.05279/) (2021)
- [Survey of Social Bias in Vision-Language Models](https://mlsanity.com/paper/2309.14381/) (2023)
- [Procrustean Training for Imbalanced Deep Learning](https://mlsanity.com/paper/2104.01769/) (2021)
- [Balanced Knowledge Distillation for Long-tailed Learning](https://mlsanity.com/paper/2104.10510/) (2021)
- [Dual Spoof Disentanglement Generation for Face Anti-spoofing with Depth Uncertainty Learning](https://mlsanity.com/paper/2112.00568/) (2021)
- [Uncertainty-Calibrated Test-Time Model Adaptation without Forgetting](https://mlsanity.com/paper/2403.11491/) (2024)
- [FairCal: Fairness Calibration for Face Verification](https://mlsanity.com/paper/2106.03761/) (2021)
- [On-target Adaptation](https://mlsanity.com/paper/2109.01087/) (2021)
- [Hierarchical Memory Learning for Fine-Grained Scene Graph Generation](https://mlsanity.com/paper/2203.06907/) (2022)
- [Balancing the Scales: A Theoretical and Algorithmic Framework for Learning from Imbalanced Data](https://mlsanity.com/paper/2502.10381/) (2025)
- [FIFA: Making Fairness More Generalizable in Classifiers Trained on Imbalanced Data](https://mlsanity.com/paper/2206.02792/) (2022)
- [Reliability-Aware Prediction via Uncertainty Learning for Person Image Retrieval](https://mlsanity.com/paper/2210.13440/) (2022)
- [InPL: Pseudo-labeling the Inliers First for Imbalanced Semi-supervised Learning](https://mlsanity.com/paper/2303.07269/) (2023)
- [Predicate correlation learning for scene graph generation](https://mlsanity.com/paper/2107.02713/) (2021)
- [Epistemic Uncertainty-Weighted Loss for Visual Bias Mitigation](https://mlsanity.com/paper/2204.09389/) (2022)

## Abstract (arXiv)

Learning unbiased models on imbalanced datasets is a significant challenge. Rare classes tend to get a concentrated representation in the classification space which hampers the generalization of learned boundaries to new test examples. In this paper, we demonstrate that the Bayesian uncertainty estimates directly correlate with the rarity of classes and the difficulty level of individual samples. Subsequently, we present a novel framework for uncertainty based class imbalance learning that follows two key insights: First, classification boundaries should be extended further away from a more uncertain (rare) class to avoid overfitting and enhance its generalization. Second, each sample should be modeled as a multi-variate Gaussian distribution with a mean vector and a covariance matrix defined by the sample's uncertainty. The learned boundaries should respect not only the individual samples but also their distribution in the feature space. Our proposed approach efficiently utilizes sample and class uncertainty information to learn robust features and more generalizable classifiers. We systematically study the class imbalance problem and derive a novel loss formulation for max-margin learning based on Bayesian uncertainty measure. The proposed method shows significant performance improvements on six benchmark datasets for face verification, attribute prediction, digit/object classification and skin lesion detection.