Re-labeling ImageNet: from Single to Multi-Labels, from Global to Localized Labels
Open paper
Benchmark
Model
Rank
Results
image-classification-on-imagenet
ReXNet_1.0-relabel
#788
Top 1 Accuracy: 78.4%
Number of params: 4.8M
image-classification-on-omnibenchmark
ReLabel
#20
Average Top-1 Accuracy: 30.8
Rank counts only results with a code link.