Image Classification on CIFAR-100-LT (Reverse split)
83.1AccuracyFixMatch + AdaptFormer + DECON
Evaluation results
| Method | Links | |
|---|---|---|
| FixMatch + AdaptFormer + DECONFine-tuning strategy=AdaptFormer, Pre-trained model=CLIP2024.06 | 83.1 | |
| FixMatch + VPT + DECONFine-tuning strategy=Visual Prompt Tuning (VPT), Pre-trained model=CLIP2024.06 | 81.9 | |
| FixMatch + AdaptFormer + ACRFine-tuning strategy=AdaptFormer, Pre-trained model=CLIP2024.06 | 81.4 | |
| FixMatch + VPT + ACRFine-tuning strategy=Visual Prompt Tuning (VPT), Pre-trained model=CLIP2024.06 | 80.3 | |
| FixMatch + AdaptFormerFine-tuning strategy=AdaptFormer, Pre-trained model=CLIP2024.06 | 80.2 | |
| FixMatch + VPTFine-tuning strategy=Visual Prompt Tuning (VPT), Pre-trained model=CLIP2024.06 | 79.7 |