DeepAI AI Chat
Log In Sign Up

Graph-guided Architecture Search for Real-time Semantic Segmentation

09/15/2019
by   Peiwen Lin, et al.
SenseTime Corporation
Zhejiang University
0

Designing a lightweight semantic segmentation network often requires researchers to find a trade-off between performance and speed, which is always empirical due to the limited interpretability of neural networks. In order to release researchers from these tedious mechanical trials, we propose a Graph-guided Architecture Search (GAS) pipeline to automatically search real-time semantic segmentation networks. 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. Specifically, to produce the cell-level diversity, the cell-sharing constraint is eliminated through the cell-independent manner. Then a graph convolution network (GCN) is seamlessly integrated as a communication mechanism between cells. Finally, a latency-oriented constraint is endowed into the search process to balance the speed and performance. Extensive experiments on Cityscapes and CamVid datasets demonstrate that GAS achieves new state-of-the-art trade-off between accuracy and speed. In particular, on Cityscapes dataset, GAS achieves the new best performance of 73.3

READ FULL TEXT
02/16/2023

Local-to-Global Information Communication for Real-Time Semantic Segmentation Network Search

Neural Architecture Search (NAS) has shown great potentials in automatic...
08/26/2019

Customizable Architecture Search for Semantic Segmentation

In this paper, we propose a Customizable Architecture Search (CAS) appro...
03/09/2019

Partial Order Pruning: for Best Speed/Accuracy Trade-off in Neural Architecture Search

Achieving good speed and accuracy trade-off on target platform is very i...
12/23/2019

FasterSeg: Searching for Faster Real-time Semantic Segmentation

We present FasterSeg, an automatically designed semantic segmentation ne...
08/10/2022

Efficient Joint-Dimensional Search with Solution Space Regularization for Real-Time Semantic Segmentation

Semantic segmentation is a popular research topic in computer vision, an...
03/31/2020

Real-Time Semantic Segmentation via Auto Depth, Downsampling Joint Decision and Feature Aggregation

To satisfy the stringent requirements on computational resources in the ...
04/09/2021

Combined Depth Space based Architecture Search For Person Re-identification

Most works on person re-identification (ReID) take advantage of large ba...