ADD-GCN

Reported on 1 benchmark across 1 task · 1 paper

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

Methodology1 result

Multi-Label ClassificationonMS-COCO
mAP· 2020-12-05
85.2
best: 93.54 (ADDS(ViT-L-336, resolution 1344))
Attention-Driven Dynamic Graph Convolutional Network for Multi-Label Image Recognition arXiv:2012.02994