{"ID":2881105,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.12877","arxiv_id":"2508.12877","title":"Preserve and Sculpt: Manifold-Aligned Fine-tuning of Vision-Language Models for Few-Shot Learning","abstract":"Pretrained vision-language models (VLMs), such as CLIP, have shown remarkable potential in few-shot image classification and led to numerous effective transfer learning strategies. These methods leverage the pretrained knowledge of VLMs to enable effective domain adaptation while mitigating overfitting through parameter-efficient tuning or instance-based consistency constraints. However, such regularizations often neglect the geometric structure of data distribution, which may lead to distortion of the overall semantic representation. To overcome this limitation, we propose a novel fine-tuning method, Manifold-Preserving and Sculpting Tuning (MPS-Tuning). Regarding the data distribution in feature space as a semantic manifold, MPS-Tuning explicitly constrains the intrinsic geometry of this manifold while further sculpting it to enhance class separability. Specifically, MPS-Tuning preserves both macroscopic and microscopic topological structures of the original manifold by aligning Gram matrices of features before and after fine-tuning. Theoretically, this constraint is shown to approximate an upper bound of the Gromov-Wasserstein distance. Furthermore, features from the image and text modalities are paired, and pairwise similarities are optimized to enhance the manifold's class discriminability. Extensive experiments demonstrate that MPS-Tuning significantly improves model performance while effectively preserving the structure of the semantic manifold. The code will be released.","short_abstract":"Pretrained vision-language models (VLMs), such as CLIP, have shown remarkable potential in few-shot image classification and led to numerous effective transfer learning strategies. These methods leverage the pretrained knowledge of VLMs to enable effective domain adaptation while mitigating overfitting through paramete...","url_abs":"https://arxiv.org/abs/2508.12877","url_pdf":"https://arxiv.org/pdf/2508.12877v1","authors":"[\"Dexia Chen\",\"Qianjie Zhu\",\"Weibing Li\",\"Yue Yu\",\"Tong Zhang\",\"Ruixuan Wang\"]","published":"2025-08-18T12:28:43Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Language Model\"]","has_code":false}