Exploring prompt tuning with pseudolabels for multiple modalities, learning settings, and training strategies.
-
Updated
Nov 8, 2024 - Python
8000
Exploring prompt tuning with pseudolabels for multiple modalities, learning settings, and training strategies.
[ICML 2024] Offical code repo for ICML2024 paper "Candidate Pseudolabel Learning: Enhancing Vision-Language Models by Prompt Tuning with Unlabeled Data"
Cross Pseudo Supervision (CPS) is a semi-supervised learning technique designed to improve semantic segmentation by leveraging unlabeled data more effectively.
Add a description, image, and links to the pseudolabels topic page so that developers can more easily learn about it.
To associate your repository with the pseudolabels topic, visit your repo's landing page and select "manage topics."