DS2VP: Dynamically-Selected Spatially Visual Prompting

The significant effectiveness of prompt tuning for computer vision tasks has been extensively demonstrated in numerous studies. As a widely feasible solution, the spatial modeling paradigm aims to overcome the limitations of sequence modeling paradigm in capturing spatial relationships within images by learning a prompt token map and aligning it spatially with the image token map. However, such spatial modeling paradigms of visual prompt tuning still face two potential challenges: 1) Most existing methods fail to design individual prompts for different images, and the learned prompts have the same static effect on all images. 2) The strategy of existing methods overlooks the selection of key spatial information and indiscriminately prompts all information within the image. In this work, we propose a novel Dynamically-Selected and Spatial Visual Prompting, termed as DS²VP, which aims to effectively utilize the key spatial information of the input image and enable dynamic visual prompt selection. Specifically, our DS²VP approach is meticulously designed to leverage the key index generator to filter key regions of the image for determining the spatial target of prompts, thus enabling dynamic selection of prompts for different images. By adding prompt tokens at selected key locations, an image prompt fusion module is deployed by adapting the learnable prompt tokens into the input image tokens, further achieving a fine-grained spatial alignment. Moreover, we propose a multi-level prompt interaction module that facilitates interactions between visual prompts at different levels to enhance feature representations across various semantic levels. Extensive experiments on two challenging benchmarks for image classification have demonstrated the superiority of DS²VP over other state-of-the-art methods for visual prompt tuning.