NAVER: A Neuro-Symbolic Compositional Automaton for Visual Grounding with Explicit Logic Reasoning
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866916897189003264 |
|---|---|
| author | Cai, Zhixi Ke, Fucai Jahangard, Simindokht de la Banda, Maria Garcia Haffari, Reza Stuckey, Peter J. Rezatofighi, Hamid |
| author_facet | Cai, Zhixi Ke, Fucai Jahangard, Simindokht de la Banda, Maria Garcia Haffari, Reza Stuckey, Peter J. Rezatofighi, Hamid |
| contents | Visual Grounding (VG) tasks, such as referring expression detection and segmentation tasks are important for linking visual entities to context, especially in complex reasoning tasks that require detailed query interpretation. This paper explores VG beyond basic perception, highlighting challenges for methods that require reasoning like human cognition. Recent advances in large language methods (LLMs) and Vision-Language methods (VLMs) have improved abilities for visual comprehension, contextual understanding, and reasoning. These methods are mainly split into end-to-end and compositional methods, with the latter offering more flexibility. Compositional approaches that integrate LLMs and foundation models show promising performance but still struggle with complex reasoning with language-based logical representations. To address these limitations, we propose NAVER, a compositional visual grounding method that integrates explicit probabilistic logic reasoning within a finite-state automaton, equipped with a self-correcting mechanism. This design improves robustness and interpretability in inference through explicit logic reasoning. Our results show that NAVER achieves SoTA performance comparing to recent end-to-end and compositional baselines. The code is available at https://github.com/ControlNet/NAVER . |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_00372 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | NAVER: A Neuro-Symbolic Compositional Automaton for Visual Grounding with Explicit Logic Reasoning Cai, Zhixi Ke, Fucai Jahangard, Simindokht de la Banda, Maria Garcia Haffari, Reza Stuckey, Peter J. Rezatofighi, Hamid Computer Vision and Pattern Recognition Visual Grounding (VG) tasks, such as referring expression detection and segmentation tasks are important for linking visual entities to context, especially in complex reasoning tasks that require detailed query interpretation. This paper explores VG beyond basic perception, highlighting challenges for methods that require reasoning like human cognition. Recent advances in large language methods (LLMs) and Vision-Language methods (VLMs) have improved abilities for visual comprehension, contextual understanding, and reasoning. These methods are mainly split into end-to-end and compositional methods, with the latter offering more flexibility. Compositional approaches that integrate LLMs and foundation models show promising performance but still struggle with complex reasoning with language-based logical representations. To address these limitations, we propose NAVER, a compositional visual grounding method that integrates explicit probabilistic logic reasoning within a finite-state automaton, equipped with a self-correcting mechanism. This design improves robustness and interpretability in inference through explicit logic reasoning. Our results show that NAVER achieves SoTA performance comparing to recent end-to-end and compositional baselines. The code is available at https://github.com/ControlNet/NAVER . |
| title | NAVER: A Neuro-Symbolic Compositional Automaton for Visual Grounding with Explicit Logic Reasoning |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2502.00372 |