PLOT: Prompt Learning with Optimal Transport for Vision-Language Models
This work addresses the challenge of prompt engineering for vision-language models, offering a novel method to enhance few-shot learning, though it is incremental in the context of existing prompt optimization techniques.
The paper tackles the problem of learning multiple comprehensive prompts for vision-language models like CLIP to describe diverse category characteristics, proposing to apply optimal transport to align visual and textual features, resulting in improved performance on few-shot recognition tasks as demonstrated in experiments.
With the increasing attention to large vision-language models such as CLIP, there has been a significant amount of effort dedicated to building efficient prompts. Unlike conventional methods of only learning one single prompt, we propose to learn multiple comprehensive prompts to describe diverse characteristics of categories such as intrinsic attributes or extrinsic contexts. However, directly matching each prompt to the same visual feature is problematic, as it pushes the prompts to converge to one point. To solve this problem, we propose to apply optimal transport to match the vision and text modalities. Specifically, we first model images and the categories with visual and textual feature sets. Then, we apply a two-stage optimization strategy to learn the prompts. In the inner loop, we optimize the optimal transport distance to align visual features and prompts by the Sinkhorn algorithm, while in the outer loop, we learn the prompts by this distance from the supervised data. Extensive experiments are conducted on the few-shot recognition task and the improvement demonstrates the superiority of our method. The code is available at https://github.com/CHENGY12/PLOT.