DeepAI AI Chat
Log In Sign Up

Graph-guided Architecture Search for Real-time Semantic Segmentation

by   Peiwen Lin, et al.
SenseTime Corporation
Zhejiang University

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


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

Neural Architecture Search (NAS) has shown great potentials in automatic...

Customizable Architecture Search for Semantic Segmentation

In this paper, we propose a Customizable Architecture Search (CAS) appro...

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...

FasterSeg: Searching for Faster Real-time Semantic Segmentation

We present FasterSeg, an automatically designed semantic segmentation ne...

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

Semantic segmentation is a popular research topic in computer vision, an...

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

To satisfy the stringent requirements on computational resources in the ...

Combined Depth Space based Architecture Search For Person Re-identification

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