# Instance-wise Uncertainty for Class Imbalance in Semantic Segmentation

arXiv: https://arxiv.org/abs/2407.12609 · HTML: https://mlsanity.com/paper/2407.12609/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 25 of its 41 references that are in the map.
- First posted on arXiv 17 Jul 2024.

## Builds on (most cited first, 25 of 25)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles](https://mlsanity.com/paper/1612.01474/) (2016)
- [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://mlsanity.com/paper/1704.04861/) (2017)
- [Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1802.02611/) (2018)
- [Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shift](https://mlsanity.com/paper/1906.02530/) (2019)
- [A Survey of Uncertainty in Deep Neural Networks](https://mlsanity.com/paper/2107.03342/) (2021)
- [Pitfalls of In-Domain Uncertainty Estimation and Ensembling in Deep Learning](https://mlsanity.com/paper/2002.06470/) (2020)
- [Understanding Measures of Uncertainty for Adversarial Example Detection](https://mlsanity.com/paper/1803.08533/) (2018)
- [Evaluating Bayesian Deep Learning Methods for Semantic Segmentation](https://mlsanity.com/paper/1811.12709/) (2018)
- [Quantifying Aleatoric and Epistemic Uncertainty in Machine Learning: Are Conditional Entropy and Mutual Information Appropriate Measures?](https://mlsanity.com/paper/2209.03302/) (2022)
- [DropConnect Is Effective in Modeling Uncertainty of Bayesian Deep Networks](https://mlsanity.com/paper/1906.04569/) (2019)
- [On the Practicality of Deterministic Epistemic Uncertainty](https://mlsanity.com/paper/2107.00649/) (2021)
- [AutoDEUQ: Automated Deep Ensemble with Uncertainty Quantification](https://mlsanity.com/paper/2110.13511/) (2021)
- [ValUES: A Framework for Systematic Validation of Uncertainty Estimation in Semantic Segmentation](https://mlsanity.com/paper/2401.08501/) (2024)
- [Deep Semantic Segmentation for Automated Driving: Taxonomy, Roadmap and Challenges](https://mlsanity.com/paper/1707.02432/) (2017)
- [Scalable Uncertainty for Computer Vision with Functional Variational Inference](https://mlsanity.com/paper/2003.03396/) (2020)
- [Semantic Segmentation with Labeling Uncertainty and Class Imbalance](https://mlsanity.com/paper/2102.04566/) (2021)
- [U-CE: Uncertainty-aware Cross-Entropy for Semantic Segmentation](https://mlsanity.com/paper/2307.09947/) (2023)
- [Closer Look at the Uncertainty Estimation in Semantic Segmentation under Distributional Shift](https://mlsanity.com/paper/2106.00076/) (2021)
- [Calibrating for Class Weights by Modeling Machine Learning](https://mlsanity.com/paper/2205.04613/) (2022)
- [Quantifying Model Uncertainty for Semantic Segmentation using Operators in the RKHS](https://mlsanity.com/paper/2211.01999/) (2022)

## Abstract (arXiv)

Semantic segmentation is a fundamental computer vision task with a vast number of applications. State of the art methods increasingly rely on deep learning models, known to incorrectly estimate uncertainty and being overconfident in predictions, especially in data not seen during training. This is particularly problematic in semantic segmentation due to inherent class imbalance. Popular uncertainty quantification approaches are task-agnostic and fail to leverage spatial pixel correlations in uncertainty estimates, crucial in this task. In this work, a novel training methodology specifically designed for semantic segmentation is presented. Training samples are weighted by instance-wise uncertainty masks computed by an ensemble. This is shown to increase performance on minority classes, boost model generalization and robustness to domain-shift when compared to using the inverse of class proportions or no class weights at all. This method addresses the challenges of class imbalance and uncertainty estimation in semantic segmentation, potentially enhancing model performance and reliability across various applications.