Probabilistic Contrastive Learning for Long-Tailed Visual Recognition

Open paper
Benchmark Model Rank Results
long-tail-learning-on-inaturalist-2018ProCo (ResNet50)#9Top-1 Accuracy: 75.8%
long-tail-learning-on-imagenet-ltProCo (ResNet50)#14Top-1 Accuracy: 60.2
long-tail-learning-on-imagenet-ltProCo (ResNeXt50)#24Top-1 Accuracy: 58.0

Rank counts only results with a code link.