CoT-Segmenter: Enhancing OOD Detection in Dense Road Scenes via Chain-of-Thought Reasoning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Song, Jeonghyo, Yun, Kimin, Jo, DaeUng, Kim, Jinyoung, Yoo, Youngjoon
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911111923630080
author Song, Jeonghyo
Yun, Kimin
Jo, DaeUng
Kim, Jinyoung
Yoo, Youngjoon
author_facet Song, Jeonghyo
Yun, Kimin
Jo, DaeUng
Kim, Jinyoung
Yoo, Youngjoon
contents Effective Out-of-Distribution (OOD) detection is criti-cal for ensuring the reliability of semantic segmentation models, particularly in complex road environments where safety and accuracy are paramount. Despite recent advancements in large language models (LLMs), notably GPT-4, which significantly enhanced multimodal reasoning through Chain-of-Thought (CoT) prompting, the application of CoT-based visual reasoning for OOD semantic segmentation remains largely unexplored. In this paper, through extensive analyses of the road scene anomalies, we identify three challenging scenarios where current state-of-the-art OOD segmentation methods consistently struggle: (1) densely packed and overlapping objects, (2) distant scenes with small objects, and (3) large foreground-dominant objects. To address the presented challenges, we propose a novel CoT-based framework targeting OOD detection in road anomaly scenes. Our method leverages the extensive knowledge and reasoning capabilities of foundation models, such as GPT-4, to enhance OOD detection through improved image understanding and prompt-based reasoning aligned with observed problematic scene attributes. Extensive experiments show that our framework consistently outperforms state-of-the-art methods on both standard benchmarks and our newly defined challenging subset of the RoadAnomaly dataset, offering a robust and interpretable solution for OOD semantic segmentation in complex driving environments.
format Preprint
id arxiv_https___arxiv_org_abs_2507_03984
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle CoT-Segmenter: Enhancing OOD Detection in Dense Road Scenes via Chain-of-Thought Reasoning
Song, Jeonghyo
Yun, Kimin
Jo, DaeUng
Kim, Jinyoung
Yoo, Youngjoon
Computer Vision and Pattern Recognition
Effective Out-of-Distribution (OOD) detection is criti-cal for ensuring the reliability of semantic segmentation models, particularly in complex road environments where safety and accuracy are paramount. Despite recent advancements in large language models (LLMs), notably GPT-4, which significantly enhanced multimodal reasoning through Chain-of-Thought (CoT) prompting, the application of CoT-based visual reasoning for OOD semantic segmentation remains largely unexplored. In this paper, through extensive analyses of the road scene anomalies, we identify three challenging scenarios where current state-of-the-art OOD segmentation methods consistently struggle: (1) densely packed and overlapping objects, (2) distant scenes with small objects, and (3) large foreground-dominant objects. To address the presented challenges, we propose a novel CoT-based framework targeting OOD detection in road anomaly scenes. Our method leverages the extensive knowledge and reasoning capabilities of foundation models, such as GPT-4, to enhance OOD detection through improved image understanding and prompt-based reasoning aligned with observed problematic scene attributes. Extensive experiments show that our framework consistently outperforms state-of-the-art methods on both standard benchmarks and our newly defined challenging subset of the RoadAnomaly dataset, offering a robust and interpretable solution for OOD semantic segmentation in complex driving environments.
title CoT-Segmenter: Enhancing OOD Detection in Dense Road Scenes via Chain-of-Thought Reasoning
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2507.03984