Bridging the Semantic Chasm: Synergistic Conceptual Anchoring for Generalized Few-Shot and Zero-Shot OOD Perception
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866910006707748864 |
|---|---|
| author | Christoforos, Alexandros Jenkins, Sarah Brown, Michael Pham, Tuan Chen, David |
| author_facet | Christoforos, Alexandros Jenkins, Sarah Brown, Michael Pham, Tuan Chen, David |
| contents | This manuscript presents a pioneering Synergistic Neural Agents Network (SynerNet) framework designed to mitigate the phenomenon of cross-modal alignment degeneration in Vision-Language Models (VLMs) when encountering Out-of-Distribution (OOD) concepts. Specifically, four specialized computational units - visual perception, linguistic context, nominal embedding, and global coordination - collaboratively rectify modality disparities via a structured message-propagation protocol. The principal contributions encompass a multi-agent latent space nomenclature acquisition framework, a semantic context-interchange algorithm for enhanced few-shot adaptation, and an adaptive dynamic equilibrium mechanism. Empirical evaluations conducted on the VISTA-Beyond benchmark demonstrate that SynerNet yields substantial performance augmentations in both few-shot and zero-shot scenarios, exhibiting precision improvements ranging from 1.2% to 5.4% across a diverse array of domains. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_00340 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Bridging the Semantic Chasm: Synergistic Conceptual Anchoring for Generalized Few-Shot and Zero-Shot OOD Perception Christoforos, Alexandros Jenkins, Sarah Brown, Michael Pham, Tuan Chen, David Computer Vision and Pattern Recognition Artificial Intelligence This manuscript presents a pioneering Synergistic Neural Agents Network (SynerNet) framework designed to mitigate the phenomenon of cross-modal alignment degeneration in Vision-Language Models (VLMs) when encountering Out-of-Distribution (OOD) concepts. Specifically, four specialized computational units - visual perception, linguistic context, nominal embedding, and global coordination - collaboratively rectify modality disparities via a structured message-propagation protocol. The principal contributions encompass a multi-agent latent space nomenclature acquisition framework, a semantic context-interchange algorithm for enhanced few-shot adaptation, and an adaptive dynamic equilibrium mechanism. Empirical evaluations conducted on the VISTA-Beyond benchmark demonstrate that SynerNet yields substantial performance augmentations in both few-shot and zero-shot scenarios, exhibiting precision improvements ranging from 1.2% to 5.4% across a diverse array of domains. |
| title | Bridging the Semantic Chasm: Synergistic Conceptual Anchoring for Generalized Few-Shot and Zero-Shot OOD Perception |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2602.00340 |