MLD-TResNetL-AAM (resolution 448, pretrain from OpenImages V6)

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 ClassificationonPASCAL VOC 2007
mAP· 2022-09-14
96.7
best: 97.3 (Q2L-CvT(ImageNet-21K pretrained, resolution 384))
Combining Metric Learning and Attention Heads For Accurate and Efficient Multilabel Image Classification arXiv:2209.06585