Tasks SotA Datasets Papers Methods Submit About

Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable Benchmarks All SotA Datasets Papers Methods

Community

Submit Results About

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/ViDT Swin-tiny

ViDT Swin-tiny

Reported on 30 benchmarks across 5 tasks · 1 paper

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

Methodology24 results

3DonCOCO 2017 val
AP· 2021-10-08
44.8
best: 72.2 (LOGO-CAP (Ours) HRNet-W48)
ViDT: An Efficient and Effective Fully Transformer-based Object Detector arXiv:2110.03921
3DonCOCO 2017 val
AP50· 2021-10-08
64.5
best: 79 (Mr. DETR (Swin-L, 1x, 5cale))
ViDT: An Efficient and Effective Fully Transformer-based Object Detector arXiv:2110.03921
3DonCOCO 2017 val
AP75· 2021-10-08
48.7
best: 67.6 (Mr. DETR (Swin-L, 1x, 5cale))
ViDT: An Efficient and Effective Fully Transformer-based Object Detector arXiv:2110.03921
3DonCOCO 2017 val
APL· 2021-10-08
62.1
best: 75.7 (Mr. DETR (Swin-L, 1x, 5cale))
ViDT: An Efficient and Effective Fully Transformer-based Object Detector arXiv:2110.03921
3DonCOCO 2017 val
APM· 2021-10-08
47.6
best: 65.6 (Mr. DETR (Swin-L, 1x, 5cale))
ViDT: An Efficient and Effective Fully Transformer-based Object Detector arXiv:2110.03921
3DonCOCO 2017 val
APS· 2021-10-08
25.9
best: 47.7 (Mr. DETR (Swin-L, 1x, 5cale))
ViDT: An Efficient and Effective Fully Transformer-based Object Detector arXiv:2110.03921
2D ClassificationonCOCO 2017 val
AP· 2021-10-08
44.8
best: 61.8 (Mr. DETR (Swin-L, 1x, 5cale))
ViDT: An Efficient and Effective Fully Transformer-based Object Detector arXiv:2110.03921
2D ClassificationonCOCO 2017 val
AP50· 2021-10-08
64.5
best: 79 (Mr. DETR (Swin-L, 1x, 5cale))
ViDT: An Efficient and Effective Fully Transformer-based Object Detector arXiv:2110.03921
2D ClassificationonCOCO 2017 val
AP75· 2021-10-08
48.7
best: 67.6 (Mr. DETR (Swin-L, 1x, 5cale))
ViDT: An Efficient and Effective Fully Transformer-based Object Detector arXiv:2110.03921
2D ClassificationonCOCO 2017 val
APL· 2021-10-08
62.1
best: 75.7 (Mr. DETR (Swin-L, 1x, 5cale))
ViDT: An Efficient and Effective Fully Transformer-based Object Detector arXiv:2110.03921
2D ClassificationonCOCO 2017 val
APM· 2021-10-08
47.6
best: 65.6 (Mr. DETR (Swin-L, 1x, 5cale))
ViDT: An Efficient and Effective Fully Transformer-based Object Detector arXiv:2110.03921
2D ClassificationonCOCO 2017 val
APS· 2021-10-08
25.9
best: 47.7 (Mr. DETR (Swin-L, 1x, 5cale))
ViDT: An Efficient and Effective Fully Transformer-based Object Detector arXiv:2110.03921
2D Object DetectiononCOCO 2017 val
AP· 2021-10-08
44.8
best: 61.8 (Mr. DETR (Swin-L, 1x, 5cale))
ViDT: An Efficient and Effective Fully Transformer-based Object Detector arXiv:2110.03921
2D Object DetectiononCOCO 2017 val
AP50· 2021-10-08
64.5
best: 79 (Mr. DETR (Swin-L, 1x, 5cale))
ViDT: An Efficient and Effective Fully Transformer-based Object Detector arXiv:2110.03921
2D Object DetectiononCOCO 2017 val
AP75· 2021-10-08
48.7
best: 67.6 (Mr. DETR (Swin-L, 1x, 5cale))
ViDT: An Efficient and Effective Fully Transformer-based Object Detector arXiv:2110.03921
2D Object DetectiononCOCO 2017 val
APL· 2021-10-08
62.1
best: 75.7 (Mr. DETR (Swin-L, 1x, 5cale))
ViDT: An Efficient and Effective Fully Transformer-based Object Detector arXiv:2110.03921
2D Object DetectiononCOCO 2017 val
APM· 2021-10-08
47.6
best: 65.6 (Mr. DETR (Swin-L, 1x, 5cale))
ViDT: An Efficient and Effective Fully Transformer-based Object Detector arXiv:2110.03921
2D Object DetectiononCOCO 2017 val
APS· 2021-10-08
25.9
best: 47.7 (Mr. DETR (Swin-L, 1x, 5cale))
ViDT: An Efficient and Effective Fully Transformer-based Object Detector arXiv:2110.03921
16konCOCO 2017 val
AP· 2021-10-08
44.8
best: 61.8 (Mr. DETR (Swin-L, 1x, 5cale))
ViDT: An Efficient and Effective Fully Transformer-based Object Detector arXiv:2110.03921
16konCOCO 2017 val
AP50· 2021-10-08
64.5
best: 79 (Mr. DETR (Swin-L, 1x, 5cale))
ViDT: An Efficient and Effective Fully Transformer-based Object Detector arXiv:2110.03921
16konCOCO 2017 val
AP75· 2021-10-08
48.7
best: 67.6 (Mr. DETR (Swin-L, 1x, 5cale))
ViDT: An Efficient and Effective Fully Transformer-based Object Detector arXiv:2110.03921
16konCOCO 2017 val
APL· 2021-10-08
62.1
best: 75.7 (Mr. DETR (Swin-L, 1x, 5cale))
ViDT: An Efficient and Effective Fully Transformer-based Object Detector arXiv:2110.03921
16konCOCO 2017 val
APM· 2021-10-08
47.6
best: 65.6 (Mr. DETR (Swin-L, 1x, 5cale))
ViDT: An Efficient and Effective Fully Transformer-based Object Detector arXiv:2110.03921
16konCOCO 2017 val
APS· 2021-10-08
25.9
best: 47.7 (Mr. DETR (Swin-L, 1x, 5cale))
ViDT: An Efficient and Effective Fully Transformer-based Object Detector arXiv:2110.03921

Computer Vision6 results

Object DetectiononCOCO 2017 val
AP· 2021-10-08
44.8
best: 61.8 (Mr. DETR (Swin-L, 1x, 5cale))
ViDT: An Efficient and Effective Fully Transformer-based Object Detector arXiv:2110.03921
Object DetectiononCOCO 2017 val
AP50· 2021-10-08
64.5
best: 79 (Mr. DETR (Swin-L, 1x, 5cale))
ViDT: An Efficient and Effective Fully Transformer-based Object Detector arXiv:2110.03921
Object DetectiononCOCO 2017 val
AP75· 2021-10-08
48.7
best: 67.6 (Mr. DETR (Swin-L, 1x, 5cale))
ViDT: An Efficient and Effective Fully Transformer-based Object Detector arXiv:2110.03921
Object DetectiononCOCO 2017 val
APL· 2021-10-08
62.1
best: 75.7 (Mr. DETR (Swin-L, 1x, 5cale))
ViDT: An Efficient and Effective Fully Transformer-based Object Detector arXiv:2110.03921
Object DetectiononCOCO 2017 val
APM· 2021-10-08
47.6
best: 65.6 (Mr. DETR (Swin-L, 1x, 5cale))
ViDT: An Efficient and Effective Fully Transformer-based Object Detector arXiv:2110.03921
Object DetectiononCOCO 2017 val
APS· 2021-10-08
25.9
best: 47.7 (Mr. DETR (Swin-L, 1x, 5cale))
ViDT: An Efficient and Effective Fully Transformer-based Object Detector arXiv:2110.03921