{"ID":2874472,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.03895","arxiv_id":"2509.03895","title":"Attn-Adapter: Attention Is All You Need for Online Few-shot Learner of Vision-Language Model","abstract":"Contrastive vision-language models excel in zero-shot image recognition but face challenges in few-shot scenarios due to computationally intensive offline fine-tuning using prompt learning, which risks overfitting. To overcome these limitations, we propose Attn-Adapter, a novel online few-shot learning framework that enhances CLIP's adaptability via a dual attention mechanism. Our design incorporates dataset-specific information through two components: the Memory Attn-Adapter, which refines category embeddings using support examples, and the Local-Global Attn-Adapter, which enriches image embeddings by integrating local and global features. This architecture enables dynamic adaptation from a few labeled samples without retraining the base model. Attn-Adapter outperforms state-of-the-art methods in cross-category and cross-dataset generalization, maintaining efficient inference and scaling across CLIP backbones.","short_abstract":"Contrastive vision-language models excel in zero-shot image recognition but face challenges in few-shot scenarios due to computationally intensive offline fine-tuning using prompt learning, which risks overfitting. To overcome these limitations, we propose Attn-Adapter, a novel online few-shot learning framework that e...","url_abs":"https://arxiv.org/abs/2509.03895","url_pdf":"https://arxiv.org/pdf/2509.03895v1","authors":"[\"Phuoc-Nguyen Bui\",\"Khanh-Binh Nguyen\",\"Hyunseung Choo\"]","published":"2025-09-04T05:42:02Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Language Model\"]","has_code":false}