YOLOX-tiny

Reported on 5 benchmarks across 5 tasks

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

Methodology4 results

3DonMSCOCO
mAP @0.5:0.95
32.8
best: 40.9 (PP-PicoDet-L)
2D ClassificationonMSCOCO
mAP @0.5:0.95
32.8
best: 40.9 (PP-PicoDet-L)
2D Object DetectiononMSCOCO
mAP @0.5:0.95
32.8
best: 40.9 (PP-PicoDet-L)
16konMSCOCO
mAP @0.5:0.95
32.8
best: 40.9 (PP-PicoDet-L)

Computer Vision1 result

Object DetectiononMSCOCO
mAP @0.5:0.95
32.8
best: 40.9 (PP-PicoDet-L)