FGT (R101, Faster RCNN)

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

3DonCityscapes
mPC [AP]· 2025-06-26
22.1
best: 27.4 (FGT (SD-1.5 Backbone))
Boosting Domain Generalized and Adaptive Detection with Diffusion Models: Fitness, Generalization, and Transferability arXiv:2506.21042
2D ClassificationonCityscapes
mPC [AP]· 2025-06-26
22.1
best: 27.4 (FGT (SD-1.5 Backbone))
Boosting Domain Generalized and Adaptive Detection with Diffusion Models: Fitness, Generalization, and Transferability arXiv:2506.21042
2D Object DetectiononCityscapes
mPC [AP]· 2025-06-26
22.1
best: 27.4 (FGT (SD-1.5 Backbone))
Boosting Domain Generalized and Adaptive Detection with Diffusion Models: Fitness, Generalization, and Transferability arXiv:2506.21042
16konCityscapes
mPC [AP]· 2025-06-26
22.1
best: 27.4 (FGT (SD-1.5 Backbone))
Boosting Domain Generalized and Adaptive Detection with Diffusion Models: Fitness, Generalization, and Transferability arXiv:2506.21042

Computer Vision1 result

Object DetectiononCityscapes
mPC [AP]· 2025-06-26
22.1
best: 27.4 (FGT (SD-1.5 Backbone))
Boosting Domain Generalized and Adaptive Detection with Diffusion Models: Fitness, Generalization, and Transferability arXiv:2506.21042