2024/09/17 by Edgar Heinert, Stephan Tilgner, Heinert, Edgar +5
Computer Science · #68T07 #Advanced Clustering Algorithms Research #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences
paper · pdf · doi:10.48550/arxiv.2409.11373
openalex publication_date 2024/09/17 · openalex created_date 2024/10/24 · openalex updated_date 2026/07/28
When employing deep neural networks (DNNs) for semantic segmentation in safety-critical applications like automotive perception or medical imaging, it is important to estimate their performance at runtime, e.g. via uncertainty estimates or prediction quality estimates. Previous works mostly performed uncertainty estimation on pixel-level. In a line of research, a connected-component-wise (segment-wise) perspective was taken, approaching uncertainty estimation on an object-level by performing so-called meta classification and regression to estimate uncertainty and prediction quality, respectively. In those works, each predicted segment is considered individually to estimate its uncertainty or prediction quality. However, the neighboring segments may provide additional hints on whether a given predicted segment is of high quality, which we study in the present work. On the basis of uncertainty indicating metrics on segment-level, we use graph neural networks (GNNs) to model the relationship of a given segment's quality as a function of the given segment's metrics as well as those of its neighboring segments. We compare different GNN architectures and achieve a notable performance improvement.