|国家预印本平台
首页|Prior2Former -- Evidential Modeling of Mask Transformers for Assumption-Free Open-World Panoptic Segmentation

Prior2Former -- Evidential Modeling of Mask Transformers for Assumption-Free Open-World Panoptic Segmentation

Prior2Former -- Evidential Modeling of Mask Transformers for Assumption-Free Open-World Panoptic Segmentation

来源:Arxiv_logoArxiv
英文摘要

In panoptic segmentation, individual instances must be separated within semantic classes. As state-of-the-art methods rely on a pre-defined set of classes, they struggle with novel categories and out-of-distribution (OOD) data. This is particularly problematic in safety-critical applications, such as autonomous driving, where reliability in unseen scenarios is essential. We address the gap between outstanding benchmark performance and reliability by proposing Prior2Former (P2F), the first approach for segmentation vision transformers rooted in evidential learning. P2F extends the mask vision transformer architecture by incorporating a Beta prior for computing model uncertainty in pixel-wise binary mask assignments. This design enables high-quality uncertainty estimation that effectively detects novel and OOD objects enabling state-of-the-art anomaly instance segmentation and open-world panoptic segmentation. Unlike most segmentation models addressing unknown classes, P2F operates without access to OOD data samples or contrastive training on void (i.e., unlabeled) classes, making it highly applicable in real-world scenarios where such prior information is unavailable. Additionally, P2F can be flexibly applied to anomaly instance and panoptic segmentation. Through comprehensive experiments on the Cityscapes, COCO, SegmentMeIfYouCan, and OoDIS datasets, we demonstrate the state-of-the-art performance of P2F. It achieves the highest ranking in the OoDIS anomaly instance benchmark among methods not using OOD data in any way.

Sebastian Schmidt、Julius K?rner、Dominik Fuchsgruber、Stefano Gasperini、Federico Tombari、Stephan Günnemann

计算技术、计算机技术

Sebastian Schmidt,Julius K?rner,Dominik Fuchsgruber,Stefano Gasperini,Federico Tombari,Stephan Günnemann.Prior2Former -- Evidential Modeling of Mask Transformers for Assumption-Free Open-World Panoptic Segmentation[EB/OL].(2025-04-07)[2025-06-14].https://arxiv.org/abs/2504.04841.点此复制

评论