Rethinking Atrous Convolution for Semantic Image Segmentation

17 Jun 2017Liang-Chieh ChenGeorge PapandreouFlorian SchroffHartwig Adam

In this work, we revisit atrous convolution, a powerful tool to explicitly adjust filter's field-of-view as well as control the resolution of feature responses computed by Deep Convolutional Neural Networks, in the application of semantic image segmentation. To handle the problem of segmenting objects at multiple scales, we design modules which employ atrous convolution in cascade or in parallel to capture multi-scale context by adopting multiple atrous rates... (read more)

PDF Abstract

Code


Evaluation Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK USES EXTRA
TRAINING DATA
COMPARE
Semantic Segmentation Cityscapes test DeepLabv3 (ResNet-101, coarse) Mean IoU (class) 81.3% # 19
Semantic Segmentation Cityscapes val DeepLabv3 (Dilated-ResNet-101) mIoU 78.5% # 8
Semantic Segmentation PASCAL VOC 2012 test DeepLabv3-JFT Mean IoU 86.9% # 3
Semantic Segmentation PASCAL VOC 2012 val DeepLabv3-JFT mIoU 82.70% # 3