Asymmetric Loss For Multi-Label Classification

In a typical multi-label setting, a picture contains on average few positive labels, and many negative ones. This positive-negative imbalance dominates the optimization process, and can lead to under-emphasizing gradients from positive labels during training, resulting in poor accuracy... (read more)

PDF Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Multi-Label Classification MS-COCO TResNet-XL (resolution 640) mAP 88.4 # 1
Multi-Label Classification MS-COCO TResNet-L (resolution 448) mAP 86.6 # 2
Multi-Label Classification NUS-WIDE TResNet-L (resolution 448) MAP 65.2 # 1
Multi-Label Classification PASCAL VOC 2007 TResNet-L (resolution 448, pretrain from ImageNet) mAP 94.6 # 4
Multi-Label Classification PASCAL VOC 2007 TResNet-L (resolution 448, pretrain from MS-COCO) mAP 95.8 # 1

Methods used in the Paper


METHOD TYPE
🤖 No Methods Found Help the community by adding them if they're not listed; e.g. Deep Residual Learning for Image Recognition uses ResNet