English

Advancing Prompt Learning through an External Layer

Computer Vision and Pattern Recognition 2024-11-18 v6

Abstract

Prompt learning represents a promising method for adapting pre-trained vision-language models (VLMs) to various downstream tasks by learning a set of text embeddings. One challenge inherent to these methods is the poor generalization performance due to the invalidity of the learned text embeddings for unseen tasks. A straightforward approach to bridge this gap is to freeze the text embeddings in prompts, which results in a lack of capacity to adapt VLMs for downstream tasks. To address this dilemma, we propose a paradigm called EnPrompt with a novel External Layer (EnLa). Specifically, we propose a textual external layer and learnable visual embeddings for adapting VLMs to downstream tasks. The learnable external layer is built upon valid embeddings of pre-trained CLIP. This design considers the balance of learning capabilities between the two branches. To align the textual and visual features, we propose a novel two-pronged approach: i) we introduce the optimal transport as the discrepancy metric to align the vision and text modalities, and ii) we introduce a novel strengthening feature to enhance the interaction between these two modalities. Four representative experiments (i.e., base-to-novel generalization, few-shot learning, cross-dataset generalization, domain shifts generalization) across 15 datasets demonstrate that our method outperforms the existing prompt learning method.

Keywords

Cite

@article{arxiv.2407.19674,
  title  = {Advancing Prompt Learning through an External Layer},
  author = {Fangming Cui and Xun Yang and Chao Wu and Liang Xiao and Xinmei Tian},
  journal= {arXiv preprint arXiv:2407.19674},
  year   = {2024}
}
R2 v1 2026-06-28T17:56:14.205Z