Hallucination Elimination and Semantic Enhancement Framework for Vision-Language Models in Traffic Scenarios

TL;DR

This paper introduces HCOENet, a chain-of-thought correction framework that reduces hallucinations and enhances semantic understanding in vision-language models for traffic scenarios, improving accuracy and reliability.

Contribution

HCOENet is a novel plug-and-play correction method that filters hallucinated entities and extracts critical objects, advancing multimodal understanding in autonomous driving contexts.

Findings

HCOENet improves F1-score by 12.58% on Mini-InternVL-4B.

HCOENet enhances description quality with reduced computational costs.

Created new datasets CODA_desc and nuScenes_desc for traffic scene understanding.

Abstract

Large vision-language models (LVLMs) have demonstrated remarkable capabilities in multimodal understanding and generation tasks. However, these models occasionally generate hallucinatory texts, resulting in descriptions that seem reasonable but do not correspond to the image. This phenomenon can lead to wrong driving decisions of the autonomous driving system. To address this challenge, this paper proposes HCOENet, a plug-and-play chain-of-thought correction method designed to eliminate object hallucinations and generate enhanced descriptions for critical objects overlooked in the initial response. Specifically, HCOENet employs a cross-checking mechanism to filter entities and directly extracts critical objects from the given image, enriching the descriptive text. Experimental results on the POPE benchmark demonstrate that HCOENet improves the F1-score of the Mini-InternVL-4B and mPLUG-Owl3 models by 12.58% and 4.28%, respectively. Additionally, qualitative results using images collected in open campus scene further highlight the practical applicability of the proposed method. Compared with the GPT-4o model, HCOENet achieves comparable descriptive performance while significantly reducing costs. Finally, two novel semantic understanding datasets, CODA_desc and nuScenes_desc, are created for traffic scenarios to support future research. The codes and datasets are publicly available at https://github.com/fjq-tongji/HCOENet.