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|
We propose to use a convolutional neural network for real time semantic segmentation of users bodies in the stereoscopic RGB video streams acquired from the perspective of the user.
(ii) On the GPU, two Convolutional Neural Networks: A main segmentation network that is used to predict dense semantic labels from scratch, and a Refiner that is designed to improve predictions from previous frames with the help of a fast Inconsistencies Attention Module (IAM).
Specifically, it achieves 77. 1% Mean IOU on the Cityscapes test dataset with the speed of 41 FPS for a 1024*2048 input, and 75. 4% Mean IOU with the speed of 91 FPS on the Camvid test dataset.
Although current deep learning methods have achieved impressive results for semantic segmentation, they incur high computational costs and have a huge number of parameters.
Unlike previous works that use a simplified search space and stack a repeatable cell to form a network, we introduce a novel search mechanism with new search space where a lightweight model can be effectively explored through the cell-level diversity and latencyoriented constraint.
Furthermore, we make a detailed analysis and comparison of the three proposed methods on the promotion of recall rate.
The whole network has nearly symmetric architecture, which is mainly composed of a series of factorized convolution unit (FCU) and its parallel counterparts (PFCU).
#7 best model for Real-Time Semantic Segmentation on Cityscapes test
This paper introduces an extremely efficient CNN architecture named DFANet for semantic segmentation under resource constraints.
In this work, we present a random forest framework that learns the weights, shapes, and sparsities of feature representations for real-time semantic segmentation.
Semantic segmentation remains a computationally intensive algorithm for embedded deployment even with the rapid growth of computation power.