ML-GCN (pretrain from ImageNet)

Reported on 1 benchmark across 1 task · 1 paper · 1 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Methodology1 result

Multi-Label ClassificationonPASCAL VOC 2007
mAP· 2019-04-07
94
best: 97.3 (Q2L-CvT(ImageNet-21K pretrained, resolution 384))
SOTA
Multi-Label Image Recognition with Graph Convolutional Networks arXiv:1904.03582