Ours PF-DLDL

Reported on 2 benchmarks across 1 task · 1 paper · 2 SOTA

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

Methodology2 results

Multi-Label ClassificationonPASCAL VOC 2012
mAP· 2016-11-06
92.4
best: 96.2 (Q2L-TResL(448 resolution))
SOTA
Deep Label Distribution Learning with Label Ambiguity arXiv:1611.01731
Multi-Label ClassificationonPASCAL VOC 2007
mAP· 2016-11-06
93.4
best: 97.3 (Q2L-CvT(ImageNet-21K pretrained, resolution 384))
SOTA
Deep Label Distribution Learning with Label Ambiguity arXiv:1611.01731