Real-time semantic segmentation is the task of achieving computationally efficient semantic segmentation (while maintaining a base level of accuracy).
( Image credit: TorchSeg )
|TREND||DATASET||BEST METHOD||PAPER TITLE||PAPER||CODE||COMPARE|
Although current deep learning methods have achieved impressive results for semantic segmentation, they incur high computational costs and have a huge number of parameters.
As a pixel-level prediction task, semantic segmentation needs large computational cost with enormous parameters to obtain high performance.
The whole network has nearly symmetric architecture, which is mainly composed of a series of factorized convolution unit (FCU) and its parallel counterparts (PFCU).
Ranked #12 on Real-Time Semantic Segmentation on Cityscapes test
When DiCE units are stacked to build the DiCENet model, we observe significant improvements over state-of-the-art models across various computer vision tasks including image classification, object detection, and semantic segmentation.
Ranked #17 on Semantic Segmentation on PASCAL VOC 2012 val
LEDNet: A Lightweight Encoder-Decoder Network for Real-time Semantic Segmentation
Ranked #13 on Real-Time Semantic Segmentation on Cityscapes test