MaPLe: Multi-modal Prompt Learning - CVF Open Access Overview of our proposed MaPLe (Multi-modal Prompt Learning) framework for prompt learning in V-L models MaPLe tunes both vision and language branches where only the context prompts are learned, while the rest of the model is frozen
(PDF) MaPLe: Multi-modal Prompt Learning - ResearchGate In this work, we propose Multi-modal Prompt Learning (MaPLe) for both vision and language branches to improve alignment between the vision and language representations
MaPLe: Multi-modal Prompt Learning - IEEE Xplore Pre-trained vision-language (V-L) models such as CLIP have shown excellent generalization ability to downstream tasks However, they are sensitive to the choice
MaPLe: Multi-modal Prompt Learning - OpenReview This paper provides a framework capable of Multi-modal Prompt Learning (MaPLe) via vision-language prompts Specifically, MaPLe tunes both pre-trained vision and language models through the learnable context prompts, and keep the rest parts of the models frozen
MaPLe: Multi-modal Prompt Learning [CVPR 2023] - GitHub In this work, we propose Multi-modal Prompt Learning (MaPLe) for both vision and language branches to improve alignment between the vision and language representations
CVPR 2023 Open Access Repository In this work, we propose Multi-modal Prompt Learning (MaPLe) for both vision and language branches to improve alignment between the vision and language representations