Cross entropy is the most widely used loss function for supervised training of image classification models. In this paper, we propose a novel training methodology that consistently outperforms cross entropy on supervised learning tasks across different architectures and data augmentations... (read more)

PDF Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Image Classification ImageNet ResNet-200 (Supervised Contrastive) Top 1 Accuracy 80.8% # 56
Top 5 Accuracy 95.6% # 31

Methods used in the Paper