WSGARN+SSD

Reported on 5 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.

Methodology4 results

3DonCOCO test-dev
AP50· 2017-11-22
13.6
best: 95 (ViTPose (ViTAE-G, ensemble))
Weakly Supervised Object Discovery by Generative Adversarial & Ranking Networks arXiv:1711.08174
2D ClassificationonCOCO test-dev
AP50· 2017-11-22
13.6
best: 82.1 (Plain-DETR (Swin-L))
Weakly Supervised Object Discovery by Generative Adversarial & Ranking Networks arXiv:1711.08174
2D Object DetectiononCOCO test-dev
AP50· 2017-11-22
13.6
best: 82.1 (Plain-DETR (Swin-L))
Weakly Supervised Object Discovery by Generative Adversarial & Ranking Networks arXiv:1711.08174
16konCOCO test-dev
AP50· 2017-11-22
13.6
best: 82.1 (Plain-DETR (Swin-L))
Weakly Supervised Object Discovery by Generative Adversarial & Ranking Networks arXiv:1711.08174

Computer Vision1 result

Object DetectiononCOCO test-dev
AP50· 2017-11-22
13.6
best: 82.1 (Plain-DETR (Swin-L))
Weakly Supervised Object Discovery by Generative Adversarial & Ranking Networks arXiv:1711.08174