Gated-SCNN: Gated Shape CNNs for Semantic Segmentation

ICCV 2019 Towaki TakikawaDavid AcunaVarun JampaniSanja Fidler

Current state-of-the-art methods for image segmentation form a dense image representation where the color, shape and texture information are all processed together inside a deep CNN. This however may not be ideal as they contain very different type of information relevant for recognition... (read more)

PDF Abstract

Results from the Paper


Ranked #12 on Semantic Segmentation on Cityscapes test (using extra training data)

     Get a GitHub badge
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK USES EXTRA
TRAINING DATA
RESULT BENCHMARK
Semantic Segmentation Cityscapes test Gated-SCNN Mean IoU (class) 82.8% # 12
Semantic Segmentation Cityscapes val GSCNN (ResNet-50) mIoU 73.0% # 21
Semantic Segmentation Cityscapes val GSCNN (ResNet-101) mIoU 74.7% # 18

Methods used in the Paper