Segment Every Out-of-Distribution Object

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhao, Wenjie, Li, Jia, Dong, Xin, Xiang, Yu, Guo, Yunhui
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917624525357056
author Zhao, Wenjie
Li, Jia
Dong, Xin
Xiang, Yu
Guo, Yunhui
author_facet Zhao, Wenjie
Li, Jia
Dong, Xin
Xiang, Yu
Guo, Yunhui
contents Semantic segmentation models, while effective for in-distribution categories, face challenges in real-world deployment due to encountering out-of-distribution (OoD) objects. Detecting these OoD objects is crucial for safety-critical 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 \textbf{S}core \textbf{T}o segmentation \textbf{M}ask, 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-If-You-Can, and RoadAnomaly datasets.
format Preprint
id arxiv_https___arxiv_org_abs_2311_16516
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Segment Every Out-of-Distribution Object
Zhao, Wenjie
Li, Jia
Dong, Xin
Xiang, Yu
Guo, Yunhui
Computer Vision and Pattern Recognition
Semantic segmentation models, while effective for in-distribution categories, face challenges in real-world deployment due to encountering out-of-distribution (OoD) objects. Detecting these OoD objects is crucial for safety-critical 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 \textbf{S}core \textbf{T}o segmentation \textbf{M}ask, 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-If-You-Can, and RoadAnomaly datasets.
title Segment Every Out-of-Distribution Object
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2311.16516