APLe: Token-Wise Adaptive for Multi-Modal Prompt Learning

TL;DR

APLe introduces a token-wise adaptive method for multi-modal prompt learning in vision-language models, sequentially tuning vision and language prompts to enhance generalization and robustness across tasks.

Contribution

It proposes a novel sequential training approach for multi-modal prompts, improving generalization and robustness in vision-language models like CLIP.

Findings

Achieves competitive performance with state-of-the-art methods.

Demonstrates robustness in prompt-length experiments.

Outperforms existing prompt tuning approaches in generalization.

Abstract

Pre-trained Vision-Language (V-L) models set the benchmark for generalization to downstream tasks among the noteworthy contenders. Many characteristics of the V-L model have been explored in existing research including the challenge of the sensitivity to text input and the tuning process across multi-modal prompts. With the advanced utilization of the V-L model like CLIP, recent approaches deploy learnable prompts instead of hand-craft prompts to boost the generalization performance and address the aforementioned challenges. Inspired by layer-wise training, which is wildly used in image fusion, we note that using a sequential training process to adapt different modalities branches of CLIP efficiently facilitates the improvement of generalization. In the context of addressing the multi-modal prompting challenge, we propose Token-wise Adaptive for Multi-modal Prompt Learning (APLe) for tuning both modalities prompts, vision and language, as tokens in a sequential manner. APLe addresses the challenges in V-L models to promote prompt learning across both modalities, which indicates a competitive generalization performance in line with the state-of-the-art. Preeminently, APLe shows robustness and favourable performance in prompt-length experiments with an absolute advantage in adopting the V-L models.