# MetaFusion: Controlled False-Negative Reduction of Minority Classes in Semantic Segmentation

arXiv: https://arxiv.org/abs/1912.07420 · HTML: https://mlsanity.com/paper/1912.07420/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Dec 2019.

## Built on by (most cited first, 8 of 8)

- [Automated Detection of Label Errors in Semantic Segmentation Datasets via Deep Learning and Uncertainty Quantification](https://mlsanity.com/paper/2207.06104/) (2022)
- [Gradient-Based Quantification of Epistemic Uncertainty for Deep Object Detectors](https://mlsanity.com/paper/2107.04517/) (2021)
- [False Negative Reduction in Video Instance Segmentation using Uncertainty Estimates](https://mlsanity.com/paper/2106.14474/) (2021)
- [False Negative Reduction in Semantic Segmentation under Domain Shift using Depth Estimation](https://mlsanity.com/paper/2207.03513/) (2022)
- [Lung-DETR: Deformable Detection Transformer for Sparse Lung Nodule Anomaly Detection](https://mlsanity.com/paper/2409.05200/) (2024)
- [False Positive Detection and Prediction Quality Estimation for LiDAR Point Cloud Segmentation](https://mlsanity.com/paper/2110.15681/) (2021)
- [Uncertainty Quantification and Resource-Demanding Computer Vision Applications of Deep Learning](https://mlsanity.com/paper/2205.14917/) (2022)
- [Neural Network Meta Classifier: Improving the Reliability of Anomaly Segmentation](https://mlsanity.com/paper/2412.10765/) (2024)

## Abstract (arXiv)

In semantic segmentation datasets, classes of high importance are oftentimes underrepresented, e.g., humans in street scenes. Neural networks are usually trained to reduce the overall number of errors, attaching identical loss to errors of all kinds. However, this is not necessarily aligned with human intuition. For instance, an overlooked pedestrian seems more severe than an incorrectly detected one. One possible remedy is to deploy different decision rules by introducing class priors which assigns larger weight to underrepresented classes. While reducing the false-negatives of the underrepresented class, at the same time this leads to a considerable increase of false-positive indications. In this work, we combine decision rules with methods for false-positive detection. We therefore fuse false-negative detection with uncertainty based false-positive meta classification. We present proof-of-concept results for CIFAR-10, and prove the efficiency of our method for the semantic segmentation of street scenes on the Cityscapes dataset based on predicted instances of the 'human' class. In the latter we employ an advanced false-positive detection method using uncertainty measures aggregated over instances. We thereby achieve improved trade-offs between false-negative and false-positive samples of the underrepresented classes.