SOLQ (ResNet101, single scale)

Reported on 6 benchmarks across 6 tasks · 1 paper

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

Methodology4 results

3DonCOCO test-dev
box mAP· 2021-06-04
48.7
best: 66 (Co-DETR)
SOLQ: Segmenting Objects by Learning Queries arXiv:2106.02351
2D ClassificationonCOCO test-dev
box mAP· 2021-06-04
48.7
best: 66 (Co-DETR)
SOLQ: Segmenting Objects by Learning Queries arXiv:2106.02351
2D Object DetectiononCOCO test-dev
box mAP· 2021-06-04
48.7
best: 66 (Co-DETR)
SOLQ: Segmenting Objects by Learning Queries arXiv:2106.02351
16konCOCO test-dev
box mAP· 2021-06-04
48.7
best: 66 (Co-DETR)
SOLQ: Segmenting Objects by Learning Queries arXiv:2106.02351

Computer Vision2 results

Object DetectiononCOCO test-dev
box mAP· 2021-06-04
48.7
best: 66 (Co-DETR)
SOLQ: Segmenting Objects by Learning Queries arXiv:2106.02351
Instance SegmentationonCOCO test-dev
mask AP· 2021-06-04
40.9
best: 57.1 (Co-DETR)
SOLQ: Segmenting Objects by Learning Queries arXiv:2106.02351