ObjectNet

Benchmarks

Task Name	Dataset Name	SOTA Result
Image Classification	ObjectNet	Top-1 Accuracy84.9	219
Image Classification	ObjectNet (test)	R@152	43
Class-Incremental Learning	ObjectNet	Average Accuracy83.8	40
Image Classification	ObjectNet (val)	Top-1 Acc87.6	12
Selective classification	ObjectNet (ON)	AURC0.333	11
Image Classification	ObjectNet-9 distribution-shifted (test)	Test Accuracy31.38	10
Uncertainty Quantification for Object Classification in Unusual Poses	ObjectNet (test)	Rejection Accuracy @ 90%68.7	9
Image Classification	ObjectNet (OOD)	Top-1 Acc39.9	9
Class Incremental Learning	ObjectNet Inc-10 B-0 (test)	Favg11.2	7
Class Incremental Learning	ObjectNet Inc-5 B-0 (test)	Favg11.55	7
Class-Incremental Learning	ObjectNet 20 steps (incremental)	Average Accuracy68.12	7
Image Classification	ObjectNet 1.0 (test)	Top-1 Accuracy72.3	7
Untargeted Score-based Black-box Attack	ObjectNet	ASR100	6
Targeted Score-based Black-box Attack	ObjectNet	ASR57.5	6
Class Incremental Learning	ObjectNet Inc10 (test)	Average Accuracy71	6
Image Classification	ObjectNet 113 shared classes	Accuracy69.2	5
Image Classification	ObjectNet latest (test)	Top-1 Acc26.6	5
Class Incremental Learning	ObjectNet B-0	Last Accuracy (Alast)67.53	4
Classification	ObjectNet (ObjNet) (test)	Top-1 Accuracy21	4
Continual Learning	ObjectNet (OB)	Accuracy83.8	3
Image Classification	ObjectNet v1 (val)	Top-1 Accuracy42.62	3
Image Classification	ObjectNet standard (test)	Top-1 Acc72	2
Continual Learning	ObjectNet (OB) (test)	Accuracy-	0

Showing 23 of 23 rows