A Comparative Evaluation of Large Vision-Language Models for 2D Object Detection under SOTIF Conditions
It addresses safety risks in automated vehicles by comparing semantic reasoning models against traditional detectors, but it is incremental as it focuses on evaluation rather than introducing new methods.
This paper evaluated ten large vision-language models for 2D object detection under safety-critical conditions, finding that top models like Gemini 3 and Doubao improved recall by over 25% compared to a YOLO baseline in complex scenarios, though the baseline was more precise for synthetic perturbations.
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.