ResearchBenchmarksImage Classification on DTD (unseen)Image Classification on DTD (unseen)Follow59.9AccuracyCLIP40.431245.485650.5455.5944Nov 26, 2023Evaluation resultsMethodMethodLinksAccuracyASRCLIPBackbone=ViT-B/16, mod...Backbone=ViT-B/16, mode=zero-shot2023.1159.9—CoCoOpBackbone=ViT-B/16, Sho...Backbone=ViT-B/16, Shots=162023.1156—BadCLIPBackbone=ViT-B/16, Sho...Backbone=ViT-B/16, Shots=16, Context length=4, Maximum noise strength (epsilon)=42023.1149.7796.93CoOpBackbone=ViT-B/16, Sho...Backbone=ViT-B/16, Shots=162023.1141.18—