Segment Every Out-of-Distribution Object

Wenjie Zhao, Jia Li, Xin Dong, Yu Xiang, Yunhui Guo

Abstract: Semantic segmentation models, while effective for indistribution categories, face challenges in real-world deployment due to encountering out-of-distribution (OoD) objects. Detecting these OoD objects is crucial for safetycritical applications. Existing methods rely on anomaly scores, but choosing a suitable threshold for generating masks presents difficulties and can lead to fragmentation and inaccuracy. This paper introduces a method to convert anomaly Score To segmentation Mask, called S2M, a simple and effective framework for OoD detection in semantic segmentation. Unlike assigning anomaly scores to pixels, S2M directly segments the entire OoD object. By transforming anomaly scores into prompts for a promptable segmentation model, S2M eliminates the need for threshold selection. Extensive experiments demonstrate that S2M outperforms the state-of-the-art by approximately 20% in IoU and 40% in mean F1 score, on average, across various benchmarks including Fishyscapes, Segment-Me-IfYou-Can, and RoadAnomaly datasets. Code is available at https://github.com/WenjieZhao1/S2M.