Method Details

Details for method 'MRFM'


Method overview

name MRFM
challenge pixel-level semantic labeling
details Semantic segmentation is one of the key tasks in comput- er vision, which is to assign a category label to each pixel in an image. Despite significant progress achieved recently, most existing methods still suffer from two challenging is- sues: 1) the size of objects and stuff in an image can be very diverse, demanding for incorporating multi-scale features into the fully convolutional networks (FCNs); 2) the pixel- s close to or at the boundaries of object/stuff are hard to classify due to the intrinsic weakness of convolutional net- works. To address the first issue, we propose a new Multi- Receptive Field Module (MRFM), explicitly taking multi- scale features into account. For the second issue, we design an edge-aware loss which is effective in distinguishing the boundaries of object/stuff. With these two designs, our Mul- ti Receptive Field Network achieves new state-of-the-art re- sults on two widely-used semantic segmentation benchmark datasets. Specifically, we achieve a mean IoU of 83.0% on the Cityscapes dataset and 88.4% mean IoU on the Pascal VOC2012 dataset.
publication Multi Receptive Field Network for Semantic Segmentation
Jianlong Yuan, Zelu Deng, Shu Wang, Zhenbo Luo
project page / code
used Cityscapes data fine annotations, coarse annotations
used external data
runtime n/a
subsampling no
submission date April, 2019
previous submissions


Average results

Metric Value
IoU Classes 82.9574
iIoU Classes 62.2141
IoU Categories 92.0421
iIoU Categories 82.0154


Class results

Class IoU iIoU
road 98.8 -
sidewalk 88.0024 -
building 94.2349 -
wall 63.8028 -
fence 64.7345 -
pole 72.249 -
traffic light 78.3417 -
traffic sign 81.8391 -
vegetation 94.1502 -
terrain 73.8695 -
sky 95.6843 -
person 88.3245 74.1299
rider 74.5622 54.728
car 96.4322 91.3081
truck 79.4738 47.7118
bus 92.164 57.0284
train 88.1155 53.8644
motorcycle 72.7978 51.374
bicycle 78.612 67.5684


Category results

Category IoU iIoU
flat 98.8132 -
nature 93.7504 -
object 77.6356 -
sky 95.6843 -
construction 94.11 -
human 88.3547 74.8295
vehicle 95.9461 89.2013



Download results as .csv file

Benchmark page