DINE
DINE copied to clipboard
code for our CVPR 2022 paper "DINE: Domain Adaptation from Single and Multiple Black-box Predictors"
While Fine-tuning the distilled model, the performance on the VisDA-C dataset drops, the results are as follows: ``` seed=2019: 74.98 --> 74.80 seed=2020: 76.17 --> 75.17 seed=2021: 79.8 --> 78.6....
Dear Teacher Liang Jian, I am not sure when you will release the code for ViT. Your SHOT, BA3US, SHOT++, and DINE code for resnet is excellent, especially since SHOT...
hi, can you open the instruction on office dataset?