Skip to content

Latest commit

 

History

History
 
 

fcn

Deep High-Resolution Representation Learning for Visual Recognition

Reference

Wang, Jingdong, Ke Sun, Tianheng Cheng, Borui Jiang, Chaorui Deng, Yang Zhao, Dong Liu et al. "Deep high-resolution representation learning for visual recognition." IEEE transactions on pattern analysis and machine intelligence (2020).

Performance

Cityscapes

Model Backbone Resolution Training Iters mIoU mIoU (flip) mIoU (ms+flip) Links
FCN HRNet_W18 1024x512 80000 78.97% 79.49% 79.74% model | log | vdl
FCN HRNet_W48 1024x512 80000 80.70% 81.24% 81.56% model | log | vdl

Pascal VOC 2012 + Aug

Model Backbone Resolution Training Iters mIoU mIoU (flip) mIoU (ms+flip) Links
FCN HRNet_W18 512x512 40000 75.39% 76.04% 77.09% model | log | vdl
FCN HRNet_W48 512x512 40000 78.72% 79.52% 80.10% model | log | vdl