Selective Vision-Language Subspace Projection for Few-shot CLIP

Abstract

Vision-language models such as CLIP are capable of mapping the different modality data into a unified feature space, enabling zero/few-shot inference by measuring the similarity of given images and texts. However, most existing methods overlook modality gaps in CLIP’s encoded features, which is shown as the text and image features lie far apart from each other, resulting in limited classification performance. To tackle this issue, we introduce a method called extbf{S}elective Vision-Language extbf{S}ubspace extbf{P}rojection ( extbf{SSP}), which incorporates local image features and utilizes them as a bridge to enhance the alignment between image-text pairs. Specifically, our SSP framework comprises two parallel modules: a vision projector and a language projector. Both projectors utilize local image features to span the respective subspaces for image and texts, thereby projecting the image and text features into their respective subspaces to achieve alignment. Moreover, our approach entails only training-free matrix calculations and can be seamlessly integrated into advanced CLIP-based few-shot learning frameworks. Extensive experiments on 11 datasets have demonstrated SSP’s superior text-image alignment capabilities, outperforming the state-of-the-art alignment methods.

@article{zhu2024selective,
  title={Selective Vision-Language Subspace Projection for Few-shot CLIP},
  author={Zhu, Xingyu and Zhu, Beier and Tan, Yi and Wang, Shuo and Hao, Yanbin and Zhang, Hanwang},
  booktitle={arXiv preprint arXiv:2407.16977},
  year={2024}
}

Xingyu Zhu

朱星宇

Shuo Wang

王硕 副研究员

Yanbin Hao

郝艳宾 副研究员