Self-Supervised Aggregation of Diverse Experts for Test-Agnostic Long-Tailed Recognition

Open paper
Benchmark Model Rank Results
image-classification-on-inaturalist-2018TADE (ResNet-50)#30Top-1 Accuracy: 72.9%
long-tail-learning-on-cifar-10-lt-r-10TADE#12Error Rate: 9.2
long-tail-learning-on-cifar-10-lt-r-10RIDE#19Error Rate: 10.3
long-tail-learning-on-cifar-10-lt-r-100TADE#12Error Rate: 16.2
long-tail-learning-on-cifar-100-lt-r-10TADE#14Error Rate: 36.4
long-tail-learning-on-cifar-100-lt-r-100TADE#27Error Rate: 50.2
long-tail-learning-on-cifar-100-lt-r-50TADE#18Error Rate: 46.1
long-tail-learning-on-imagenet-ltTADE(ResNeXt101-32x4d)#12Top-1 Accuracy: 61.4
long-tail-learning-on-imagenet-ltTADE(ResNeXt-50)#17Top-1 Accuracy: 58.8
long-tail-learning-on-inaturalist-2018TADE(ResNet-152)#8Top-1 Accuracy: 77%
long-tail-learning-on-inaturalist-2018TADE#24Top-1 Accuracy: 72.9%
long-tail-learning-on-places-ltTADE#13Top-1 Accuracy: 41.3Top 1 Accuracy: 40.9

Rank counts only results with a code link.