C-MIDN+FRCNN

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

3DonPASCAL VOC 2012 test
MAP
50.3
best: 70.2 (WeakSAM-MIST-DINO (with SAM))
2D ClassificationonPASCAL VOC 2012 test
MAP
50.3
best: 70.2 (WeakSAM-MIST-DINO (with SAM))
2D Object DetectiononPASCAL VOC 2012 test
MAP
50.3
best: 70.2 (WeakSAM-MIST-DINO (with SAM))
16konPASCAL VOC 2012 test
MAP
50.3
best: 70.2 (WeakSAM-MIST-DINO (with SAM))

Computer Vision1 result

Object DetectiononPASCAL VOC 2012 test
MAP
50.3
best: 70.2 (WeakSAM-MIST-DINO (with SAM))