Image Classification on CIFAR-10 LT (Reverse split)
96.8AccuracyFixMatch + AdaptFormer + DECON
Evaluation results
| Method | Links | |
|---|---|---|
| FixMatch + AdaptFormer + DECONFine-tuning strategy=AdaptFormer, Pre-trained model=CLIP2024.06 | 96.8 | |
| FixMatch + VPT + DECONFine-tuning strategy=Visual Prompt Tuning (VPT), Pre-trained model=CLIP2024.06 | 96.7 | |
| FixMatch + VPT + ACRFine-tuning strategy=Visual Prompt Tuning (VPT), Pre-trained model=CLIP2024.06 | 96.2 | |
| FixMatch + AdaptFormer + ACRFine-tuning strategy=AdaptFormer, Pre-trained model=CLIP2024.06 | 96.2 | |
| FixMatch + AdaptFormerFine-tuning strategy=AdaptFormer, Pre-trained model=CLIP2024.06 | 95.8 | |
| FixMatch + VPTFine-tuning strategy=Visual Prompt Tuning (VPT), Pre-trained model=CLIP2024.06 | 95.2 |