Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2604.03980 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866915916656148480 |
|---|---|
| author | Chen, Minglei Wang, Weilong Duan, Jiang Deng, Ye |
| author_facet | Chen, Minglei Wang, Weilong Duan, Jiang Deng, Ye |
| contents | Parameter-efficient prompt learning has become the de facto standard for adapting Vision-Language Models (VLMs) to downstream tasks. Existing approaches predominantly focus on aligning text prompts with first-order visual features (i.e., spatial feature maps). While effective for fine-grained semantic discrimination, we argue that relying solely on first-order information is insufficient for robust adaptation, as these spatially entangled features are highly susceptible to domain shifts and local noise. In this work, we propose \textbf{Gram-Anchored Prompt Learning (GAPL)} for Vision-Language Models via Second-Order Statistics, a framework that synergizes local semantic alignment with global structural consistency. Methodologically, we introduce an additional second-order statistical stream via \textbf{Gram matrices} that augments the standard first-order spatial interaction. By anchoring prompts to these second-order priors, our approach enables language representations to dynamically adapt to statistical distribution shifts across diverse domains. Extensive experiments indicate the effectiveness of the second-order features, and show compelling performances of GAPL on various benchmarks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_03980 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Gram-Anchored Prompt Learning for Vision-Language Models via Second-Order Statistics Chen, Minglei Wang, Weilong Duan, Jiang Deng, Ye Computer Vision and Pattern Recognition Artificial Intelligence Parameter-efficient prompt learning has become the de facto standard for adapting Vision-Language Models (VLMs) to downstream tasks. Existing approaches predominantly focus on aligning text prompts with first-order visual features (i.e., spatial feature maps). While effective for fine-grained semantic discrimination, we argue that relying solely on first-order information is insufficient for robust adaptation, as these spatially entangled features are highly susceptible to domain shifts and local noise. In this work, we propose \textbf{Gram-Anchored Prompt Learning (GAPL)} for Vision-Language Models via Second-Order Statistics, a framework that synergizes local semantic alignment with global structural consistency. Methodologically, we introduce an additional second-order statistical stream via \textbf{Gram matrices} that augments the standard first-order spatial interaction. By anchoring prompts to these second-order priors, our approach enables language representations to dynamically adapt to statistical distribution shifts across diverse domains. Extensive experiments indicate the effectiveness of the second-order features, and show compelling performances of GAPL on various benchmarks. |
| title | Gram-Anchored Prompt Learning for Vision-Language Models via Second-Order Statistics |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2604.03980 |