CARE: Class-Adaptive Expert Consensus for Reliable Learning with Long-Tailed Noisy Labels

Open paper
Benchmark Model Rank Results
image-classification-on-mini-webvision-1-0CARE (CLIP+LA)#1Top-1 Accuracy: 85.3ImageNet Top-1 Accuracy: 83.8
image-classification-on-mini-webvision-1-0CARE (CLIP+CE)#2Top-1 Accuracy: 84.7ImageNet Top-1 Accuracy: 83.6

Rank counts only results with a code link.