Q2L-R101(resolution 448)

Reported on 2 benchmarks across 1 task · 1 paper

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

Methodology2 results

Multi-Label ClassificationonMS-COCO
mAP· 2021-07-22
84.9
best: 93.54 (ADDS(ViT-L-336, resolution 1344))
Query2Label: A Simple Transformer Way to Multi-Label Classification arXiv:2107.10834
Multi-Label ClassificationonNUS-WIDE
MAP· 2021-07-22
65
best: 70.1 (Q2L-CvT(resolution 384, ImageNet-21K pretrained))
Query2Label: A Simple Transformer Way to Multi-Label Classification arXiv:2107.10834