paper-with-me

Classification 벤치마크

Classification on ImageNet C-OOD (class-out-of-distribution)

5개 결과 · ⬇ CSV · JSON

Detection AUROC (severity 0)

0.9915 0.9926 0.9937 0.9947 0.9958 2023-02 2026-09 ViT-L/32-384 with Max-logit — 0.9958 (2023-02-23) ViT-L/32-384 with ODIN — 0.9955 (2023-02-23) ViT-L/32-384 with Entropy — 0.9948 (2023-02-23) ViT-L/32-384 with MC Dropout — 0.9947 (2023-02-23) ViT-L/32-384 with Softmax — 0.9915 (2023-02-23) ViT-L/32-384 with Max-logit — 0.9958 (2023-02-23)
RankModel Detection AUROC (severity 0)Detection AUROC (severity 5)Detection AUROC (severity 10) PaperCodeYear
1 ViT-L/32-384 with Max-logit 0.99580.96320.7748 A framework for benchmarking class-out-of-distribution detection and its application to ImageNet mdabbah/COOD_benchmarking 2023
2 ViT-L/32-384 with ODIN 0.99550.95890.7635 A framework for benchmarking class-out-of-distribution detection and its application to ImageNet mdabbah/COOD_benchmarking 2023
3 ViT-L/32-384 with Entropy 0.99480.95140.7332 A framework for benchmarking class-out-of-distribution detection and its application to ImageNet mdabbah/COOD_benchmarking 2023
4 ViT-L/32-384 with MC Dropout 0.99470.94780.712 A framework for benchmarking class-out-of-distribution detection and its application to ImageNet mdabbah/COOD_benchmarking 2023
5 ViT-L/32-384 with Softmax 0.99150.92930.7 A framework for benchmarking class-out-of-distribution detection and its application to ImageNet mdabbah/COOD_benchmarking 2023
1–5 / 5 페이지당 10 20 50 100