False Negative Reduction in Semantic Segmentation under Domain Shift using Depth Estimation

TL;DR

This paper proposes a modular method that uses monocular depth estimation to reduce false negatives in semantic segmentation under domain shift, improving safety in applications like autonomous driving.

Contribution

It introduces a novel post-processing approach combining depth estimation and uncertainty pruning to enhance segmentation robustness across domains.

Findings

Fewer non-detected objects in key classes

Improved generalization to new domains

Modular approach compatible with existing networks

Abstract

State-of-the-art deep neural networks demonstrate outstanding performance in semantic segmentation. However, their performance is tied to the domain represented by the training data. Open world scenarios cause inaccurate predictions which is hazardous in safety relevant applications like automated driving. In this work, we enhance semantic segmentation predictions using monocular depth estimation to improve segmentation by reducing the occurrence of non-detected objects in presence of domain shift. To this end, we infer a depth heatmap via a modified segmentation network which generates foreground-background masks, operating in parallel to a given semantic segmentation network. Both segmentation masks are aggregated with a focus on foreground classes (here road users) to reduce false negatives. To also reduce the occurrence of false positives, we apply a pruning based on uncertainty estimates. Our approach is modular in a sense that it post-processes the output of any semantic segmentation network. In our experiments, we observe less non-detected objects of most important classes and an enhanced generalization to other domains compared to the basic semantic segmentation prediction.