paper-with-me

Papers

A Comparative Evaluation of Large Vision-Language Models for 2D Object Detection under SOTIF Conditions

2026-01-30 · Ji Zhou, Yilin Ding, Yongqi Zhao, Jiachen Xu, Arno Eichberger arxiv

Reliable environmental perception remains one of the main obstacles for safe operation of automated vehicles. Safety of the Intended Functionality (SOTIF) concerns safety risks from perception insufficiencies, particularly under adverse conditions where conventional detectors often falter. While Large Vision-Language Models (LVLMs) demonstrate promising semantic reasoning, their quantitative effectiveness for safety-critical 2D object detection is underexplored. This paper presents a systematic evaluation of ten representative LVLMs using the PeSOTIF dataset, a benchmark specifically curated for long-tail traffic scenarios and environmental degradations. Performance is quantitatively compared against the classical perception approach, a YOLO-based detector. Experimental results reveal a critical trade-off: top-performing LVLMs (e.g., Gemini 3, Doubao) surpass the YOLO baseline in recall by over 25% in complex natural scenarios, exhibiting superior robustness to visual degradation. Conversely, the baseline retains an advantage in geometric precision for synthetic perturbations. These findings highlight the complementary strengths of semantic reasoning versus geometric regression, supporting the use of LVLMs as high-level safety validators in SOTIF-oriented automated driving systems.

📄 PDF Abstract BibTeX arXiv:2601.22830

Code (0)

등록된 구현이 없습니다.

Tasks

2D Object Detection

Similar Papers 제목 키워드 기반

Object Counting with GPT-4o and GPT-5: A Comparative Study

2025-12-02 · Richard Füzesséry, Kaziwa Saleh, Sándor Szénási, Zoltán Vámossy arxiv

Zero-shot object counting attempts to estimate the number of object instances belonging to novel categories that the vision model performing the counting has never encountered during training. Existing methods typically …

Object Counting

Pre-training Language Models for Comparative Reasoning

2023-05-23 · Mengxia Yu, Zhihan Zhang, Wenhao Yu, Meng Jiang

Comparative reasoning is a process of comparing objects, concepts, or entities to draw conclusions, which constitutes a fundamental cognitive ability. In this paper, we propose a novel framework to pre-train language mod…

Question AnsweringQuestion GenerationQuestion-Generation

A Vision-language Framework for Comparative Reasoning in Radiology

2026-06-04 · Tengfei Zhang, Ziheng Zhao, Xiaoman Zhang, Lisong Dai 외 arxiv

Medical imaging artificial intelligence has achieved strong performance in isolated image interpretation, but remains poorly aligned with radiological practice, where diagnosis and follow-up rely on comparison across pri…

Visual Question Answering

NeuroComparatives: Neuro-Symbolic Distillation of Comparative Knowledge

2023-05-08 · Phillip Howard, Junlin Wang, Vasudev Lal, Gadi Singer 외

Comparative knowledge (e.g., steel is stronger and heavier than styrofoam) is an essential component of our world knowledge, yet understudied in prior literature. In this paper, we harvest the dramatic improvements in kn…

Knowledge DistillationvalidWorld Knowledge

Comparative Analysis of Patch Attack on VLM-Based Autonomous Driving Architectures

2026-03-09 · David Fernandez, Pedram MohajerAnsari, Amir Salarpour, Long Cheng 외 arxiv

Vision-language models are emerging for autonomous driving, yet their robustness to physical adversarial attacks remains unexplored. This paper presents a systematic framework for comparative adversarial evaluation acros…

Autonomous DrivingObject Detection