Language-Aware Soft Prompting for Vision & Language Foundation Models

This paper is on soft prompt learning for Vision \& Language (V&L) models. Similarly to their NLP counterparts, V\&L models can be adapted to a downstream task by learning soft continuous prompts using a few training examples. Current methods learn the soft prompts by minimizing a cross-entropy loss using as class weights the features obtained by passing the prompts plus the class names through the text encoder. Such methods, however, significantly overfit the training data suffering from large accuracy degradation when tested on unseen classes from the same domain. Our main contribution, in this paper, is a surprisingly simple approach to alleviate this problem: we use a second cross entropy loss to minimize the distance between the learned soft prompts and a set of hand-engineered manual prompts (obtained by prompt engineering). The proposed loss can be interpreted in multiple ways including as a regularizer, as a means for language-based augmentation, and as a way of learning more discriminative class centroids. Importantly, our formulation is inherently amenable to including, during training, virtual classes, i.e. class names for which no visual samples are available, further increasing the robustness of the learned prompts. Through extensive evaluations on 11 datasets, we show that our approach (a) significantly outperforms all prior works on soft prompting, and (b) matches and surpasses, for the first time, the accuracy on novel classes obtained by hand-crafted prompts and CLIP for the majority of the test datasets. Code will be made available.