# Application of Decision Rules for Handling Class Imbalance in Semantic Segmentation

arXiv: https://arxiv.org/abs/1901.08394 · HTML: https://mlsanity.com/paper/1901.08394/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Jan 2019.

## Built on by (most cited first, 9 of 9)

- [Constrained Optimization to Train Neural Networks on Critical and Under-Represented Classes](https://mlsanity.com/paper/2102.12894/) (2021)
- [Striking the Right Balance: Recall Loss for Semantic Segmentation](https://mlsanity.com/paper/2106.14917/) (2021)
- [AUCSeg: AUC-oriented Pixel-level Long-tail Semantic Segmentation](https://mlsanity.com/paper/2409.20398/) (2024)
- [Semantic Segmentation with Labeling Uncertainty and Class Imbalance](https://mlsanity.com/paper/2102.04566/) (2021)
- [Tailored Uncertainty Estimation for Deep Learning Systems](https://mlsanity.com/paper/2204.13963/) (2022)
- [MetaBalance: High-Performance Neural Networks for Class-Imbalanced Data](https://mlsanity.com/paper/2106.09643/) (2021)
- [α-OCC: Uncertainty-Aware Camera-based 3D Semantic Occupancy Prediction](https://mlsanity.com/paper/2406.11021/) (2024)
- [RAFT -- A Domain Adaptation Framework for RGB & LiDAR Semantic Segmentation](https://mlsanity.com/paper/2505.04529/) (2025)
- [Addressing Mark Imbalance in Integration-free Neural Marked Temporal Point Processes](https://mlsanity.com/paper/2510.20414/) (2025)

## Abstract (arXiv)

As part of autonomous car driving systems, semantic segmentation is an essential component to obtain a full understanding of the car's environment. One difficulty, that occurs while training neural networks for this purpose, is class imbalance of training data. Consequently, a neural network trained on unbalanced data in combination with maximum a-posteriori classification may easily ignore classes that are rare in terms of their frequency in the dataset. However, these classes are often of highest interest. We approach such potential misclassifications by weighting the posterior class probabilities with the prior class probabilities which in our case are the inverse frequencies of the corresponding classes in the training dataset. More precisely, we adopt a localized method by computing the priors pixel-wise such that the impact can be analyzed at pixel level as well. In our experiments, we train one network from scratch using a proprietary dataset containing 20,000 annotated frames of video sequences recorded from street scenes. The evaluation on our test set shows an increase of average recall with regard to instances of pedestrians and info signs by 25% and 23.4%, respectively. In addition, we significantly reduce the non-detection rate for instances of the same classes by 61% and 38%.