Image Classification on Five Datasets 4-shot
0.76AccuracyFully Supervised w/ RA
Evaluation results
| Method | Links | |
|---|---|---|
| Fully Supervised w/ RALearning Paradigm=FT, Backbone=OpenCLIP ViT-B/32, Retrieval Augmentation=true, Category=Ref.2025.12 | 0.76 | |
| Fully SupervisedLearning Paradigm=FT, Backbone=OpenCLIP ViT-B/32, Category=Ref.2025.12 | 0.748 | |
| SWIFTLearning Paradigm=FT, Backbone=OpenCLIP ViT-B/32, Retrieval Augmentation=true, Category=SSFSL2025.12 | 0.715 | |
| SWATLearning Paradigm=FT, Backbone=OpenCLIP ViT-B/32, Retrieval Augmentation=true, Category=FSL2025.12 | 0.674 | |
| FS-FTLearning Paradigm=FT, Backbone=OpenCLIP ViT-B/32, Category=FSL2025.12 | 0.61 | |
| DebiasPL on VLM (ours)Learning Paradigm=FT, Backbone=OpenCLIP ViT-B/32, Category=SSFSL2025.12 | 0.603 | |
| FixMatch on VLM (ours)Learning Paradigm=FT, Backbone=OpenCLIP ViT-B/32, Category=SSFSL2025.12 | 0.577 | |
| FineSSLLearning Paradigm=PL, Backbone=OpenCLIP ViT-B/32, Category=SSFSL2025.12 | 0.576 | |
| Linear ProbingLearning Paradigm=AL, Backbone=OpenCLIP ViT-B/32, Category=FSL2025.12 | 0.57 | |
| CLAPLearning Paradigm=AL, Backbone=OpenCLIP ViT-B/32, Category=FSL2025.12 | 0.569 | |
| CMLPLearning Paradigm=AL, Backbone=OpenCLIP ViT-B/32, Category=FSL2025.12 | 0.544 | |
| TaskRes(e)Learning Paradigm=AL, Backbone=OpenCLIP ViT-B/32, Category=FSL2025.12 | 0.53 | |
| PLOTLearning Paradigm=PL, Backbone=OpenCLIP ViT-B/32, Category=FSL2025.12 | 0.503 | |
| Tip-Adapter (f)Learning Paradigm=AL, Backbone=OpenCLIP ViT-B/32, Category=FSL2025.12 | 0.5 | |
| CoOpLearning Paradigm=PL, Backbone=OpenCLIP ViT-B/32, Category=FSL2025.12 | 0.488 | |
| CLIP-AdapterLearning Paradigm=AL, Backbone=OpenCLIP ViT-B/32, Category=FSL2025.12 | 0.486 | |
| DebiasPL on VLMLearning Paradigm=FT, Backbone=OpenCLIP ViT-B/32, Category=SSFSL2025.12 | 0.396 | |
| FixMatch on VLMLearning Paradigm=FT, Backbone=OpenCLIP ViT-B/32, Category=SSFSL2025.12 | 0.393 |