mccaly's picture
Upload 2805 files
985cc7f
|
raw
history blame
15.3 kB

Fully Convolutional Networks for Semantic Segmentation

Introduction

[ALGORITHM]

@article{shelhamer2017fully,
  title={Fully convolutional networks for semantic segmentation},
  author={Shelhamer, Evan and Long, Jonathan and Darrell, Trevor},
  journal={IEEE transactions on pattern analysis and machine intelligence},
  volume={39},
  number={4},
  pages={640--651},
  year={2017},
  publisher={IEEE Trans Pattern Anal Mach Intell}
}

Results and models

Cityscapes

Method Backbone Crop Size Lr schd Mem (GB) Inf time (fps) mIoU mIoU(ms+flip) download
FCN R-50-D8 512x1024 40000 5.7 4.17 72.25 73.36 model | log
FCN R-101-D8 512x1024 40000 9.2 2.66 75.45 76.58 model | log
FCN R-50-D8 769x769 40000 6.5 1.80 71.47 72.54 model | log
FCN R-101-D8 769x769 40000 10.4 1.19 73.93 75.14 model | log
FCN R-18-D8 512x1024 80000 1.7 14.65 71.11 72.91 model | log
FCN R-50-D8 512x1024 80000 - 73.61 74.24 model | log
FCN R-101-D8 512x1024 80000 - - 75.13 75.94 model | log
FCN R-18-D8 769x769 80000 1.9 6.40 70.80 73.16 model | log
FCN R-50-D8 769x769 80000 - - 72.64 73.32 model | log
FCN R-101-D8 769x769 80000 - - 75.52 76.61 model | log
FCN R-18b-D8 512x1024 80000 1.6 16.74 70.24 72.77 model | log
FCN R-50b-D8 512x1024 80000 5.6 4.20 75.65 77.59 model | log
FCN R-101b-D8 512x1024 80000 9.1 2.73 77.37 78.77 model | log
FCN R-18b-D8 769x769 80000 1.7 6.70 69.66 72.07 model | log
FCN R-50b-D8 769x769 80000 6.3 1.82 73.83 76.60 model | log
FCN R-101b-D8 769x769 80000 10.3 1.15 77.02 78.67 model | log

ADE20K

Method Backbone Crop Size Lr schd Mem (GB) Inf time (fps) mIoU mIoU(ms+flip) download
FCN R-50-D8 512x512 80000 8.5 23.49 35.94 37.94 model | log
FCN R-101-D8 512x512 80000 12 14.78 39.61 40.83 model | log
FCN R-50-D8 512x512 160000 - - 36.10 38.08 model | log
FCN R-101-D8 512x512 160000 - - 39.91 41.40 model | log

Pascal VOC 2012 + Aug

Method Backbone Crop Size Lr schd Mem (GB) Inf time (fps) mIoU mIoU(ms+flip) download
FCN R-50-D8 512x512 20000 5.7 23.28 67.08 69.94 model | log
FCN R-101-D8 512x512 20000 9.2 14.81 71.16 73.57 model | log
FCN R-50-D8 512x512 40000 - - 66.97 69.04 model | log
FCN R-101-D8 512x512 40000 - - 69.91 72.38 model | log

Pascal Context

Method Backbone Crop Size Lr schd Mem (GB) Inf time (fps) mIoU mIoU(ms+flip) download
FCN R-101-D8 480x480 40000 - 9.93 44.14 45.67 model | log
FCN R-101-D8 480x480 80000 - - 44.47 45.74 model | log