CODA-Prompt
CODA-Prompt copied to clipboard
GT-RIPL
PyTorch code for the CVPR'23 paper: "CODA-Prompt: COntinual Decomposed Attention-based Prompting for Rehearsal-Free Continual Learning"
Hi, thank you for your fantastic paper. Your work has truly impressed me. However, I find myself uncertain about a particular aspect and would greatly appreciate your guidance. Specifically, I...
Hello, as you reported in the paper, the imagenet-r with covariate domain shift is a new benchmark evaluating the semantic and covariate shift, which can be seen as a task-agnostic...
Dear author, Thank you for your fantastic work. I have a question regarding the number "200" inside the cosine scheduler. Is there a reason for setting it to be 200...
Thank you very much for providing the source code! I found that in the data preprocessing stage, the normalized mean and variance were set to 0 and 1 instead of...
The previous readme had a few typos that made the entry barrier for beginners difficult. This updates those filenames with recent changes made: cifar100.sh should be cifar-100.sh install_requirements.sh should be...
