List your company

Image Classification on ImageNet 1k (val) (Accuracy & Accuracy Gain)

77.64AccuracyMultimodal Concept-based Explanations
58.81663.70368.5973.477Oct 16, 2024

Evaluation results

MethodLinks
Multimodal Concept-based ExplanationsBackbone=ViT-L/14@336px, Zero-shot=true, Multimodal explanation descriptors=true2024.1077.642.15
Multimodal Concept-based ExplanationsBackbone=ViT-L/14, Zero-shot=true, Multimodal explanation descriptors=true2024.1076.742.05
CLIPBackbone=ViT-L/14@336px, Zero-shot=true, Multimodal explanation descriptors=false2024.1075.49—
CLIPBackbone=ViT-L/14, Zero-shot=true, Multimodal explanation descriptors=false2024.1074.69—
Multimodal Concept-based ExplanationsBackbone=RN50x16, Zero-shot=true, Multimodal explanation descriptors=true2024.1072.223.75
Multimodal Concept-based ExplanationsBackbone=ViT-B/16, Zero-shot=true, Multimodal explanation descriptors=true2024.1070.282.35
CLIPBackbone=RN50x16, Zero-shot=true, Multimodal explanation descriptors=false2024.1068.47—
Multimodal Concept-based ExplanationsBackbone=RN50x4, Zero-shot=true, Multimodal explanation descriptors=true2024.1067.933.57
CLIPBackbone=ViT-B/16, Zero-shot=true, Multimodal explanation descriptors=false2024.1067.93—
Multimodal Concept-based ExplanationsBackbone=ViT-B/32, Zero-shot=true, Multimodal explanation descriptors=true2024.1065.582.3
CLIPBackbone=RN50x4, Zero-shot=true, Multimodal explanation descriptors=false2024.1064.36—
Multimodal Concept-based ExplanationsBackbone=RN101, Zero-shot=true, Multimodal explanation descriptors=true2024.1064.143.46
CLIPBackbone=ViT-B/32, Zero-shot=true, Multimodal explanation descriptors=false2024.1063.28—
Multimodal Concept-based ExplanationsBackbone=RN50, Zero-shot=true, Multimodal explanation descriptors=true2024.1061.852.31
CLIPBackbone=RN101, Zero-shot=true, Multimodal explanation descriptors=false2024.1060.68—
CLIPBackbone=RN50, Zero-shot=true, Multimodal explanation descriptors=false2024.1059.54—