Enhancing Vision Language Models with Logic Reasoning for Situational Awareness
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912828955295744 |
|---|---|
| author | Pradeep, Pavana Kant, Krishna Yu, Suya |
| author_facet | Pradeep, Pavana Kant, Krishna Yu, Suya |
| contents | Vision-Language Models (VLMs) offer the ability to generate high-level, interpretable descriptions of complex activities from images and videos, making them valuable for situational awareness (SA) applications. In such settings, the focus is on identifying infrequent but significant events with high reliability and accuracy, while also extracting fine-grained details and assessing recognition quality. In this paper, we propose an approach that integrates VLMs with traditional computer vision methods through explicit logic reasoning to enhance SA in three key ways: (a) extracting fine-grained event details, (b) employing an intelligent fine-tuning (FT) strategy that achieves substantially higher accuracy than uninformed selection, and (c) generating justifications for VLM outputs during inference. We demonstrate that our intelligent FT mechanism improves the accuracy and provides a valuable means, during inferencing, to either confirm the validity of the VLM output or indicate why it may be questionable. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_11322 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Enhancing Vision Language Models with Logic Reasoning for Situational Awareness Pradeep, Pavana Kant, Krishna Yu, Suya Computer Vision and Pattern Recognition Logic in Computer Science Vision-Language Models (VLMs) offer the ability to generate high-level, interpretable descriptions of complex activities from images and videos, making them valuable for situational awareness (SA) applications. In such settings, the focus is on identifying infrequent but significant events with high reliability and accuracy, while also extracting fine-grained details and assessing recognition quality. In this paper, we propose an approach that integrates VLMs with traditional computer vision methods through explicit logic reasoning to enhance SA in three key ways: (a) extracting fine-grained event details, (b) employing an intelligent fine-tuning (FT) strategy that achieves substantially higher accuracy than uninformed selection, and (c) generating justifications for VLM outputs during inference. We demonstrate that our intelligent FT mechanism improves the accuracy and provides a valuable means, during inferencing, to either confirm the validity of the VLM output or indicate why it may be questionable. |
| title | Enhancing Vision Language Models with Logic Reasoning for Situational Awareness |
| topic | Computer Vision and Pattern Recognition Logic in Computer Science |
| url | https://arxiv.org/abs/2601.11322 |