Retrieval-Based Interleaved Visual Chain-of-Thought in Real-World Driving Scenarios
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866910906180435968 |
|---|---|
| author | Corbière, Charles Roburin, Simon Montariol, Syrielle Bosselut, Antoine Alahi, Alexandre |
| author_facet | Corbière, Charles Roburin, Simon Montariol, Syrielle Bosselut, Antoine Alahi, Alexandre |
| contents | While chain-of-thought (CoT) prompting improves reasoning in large language models, its effectiveness in vision-language models (VLMs) remains limited due to over-reliance on textual cues and memorized knowledge. To investigate the visual reasoning capabilities of VLMs in complex real-world scenarios, we introduce DrivingVQA, a visual question answering dataset derived from driving theory exams, which contains 3,931 multiple-choice problems with expert-written explanations and grounded entities relevant to the reasoning process. Leveraging this dataset, we propose RIV-CoT, a Retrieval-Based Interleaved Visual Chain-of-Thought method that enables VLMs to reason using visual crops corresponding to these relevant entities. Our experiments demonstrate that RIV-CoT improves answer accuracy by 3.1% and reasoning accuracy by 4.6% over vanilla CoT prompting. Furthermore, we demonstrate that our method effectively scales to the larger A-OKVQA reasoning dataset by leveraging automatically generated pseudo-labels, outperforming CoT prompting. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_04671 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Retrieval-Based Interleaved Visual Chain-of-Thought in Real-World Driving Scenarios Corbière, Charles Roburin, Simon Montariol, Syrielle Bosselut, Antoine Alahi, Alexandre Computer Vision and Pattern Recognition Artificial Intelligence While chain-of-thought (CoT) prompting improves reasoning in large language models, its effectiveness in vision-language models (VLMs) remains limited due to over-reliance on textual cues and memorized knowledge. To investigate the visual reasoning capabilities of VLMs in complex real-world scenarios, we introduce DrivingVQA, a visual question answering dataset derived from driving theory exams, which contains 3,931 multiple-choice problems with expert-written explanations and grounded entities relevant to the reasoning process. Leveraging this dataset, we propose RIV-CoT, a Retrieval-Based Interleaved Visual Chain-of-Thought method that enables VLMs to reason using visual crops corresponding to these relevant entities. Our experiments demonstrate that RIV-CoT improves answer accuracy by 3.1% and reasoning accuracy by 4.6% over vanilla CoT prompting. Furthermore, we demonstrate that our method effectively scales to the larger A-OKVQA reasoning dataset by leveraging automatically generated pseudo-labels, outperforming CoT prompting. |
| title | Retrieval-Based Interleaved Visual Chain-of-Thought in Real-World Driving Scenarios |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2501.04671 |