DeepAI AI Chat
Log In Sign Up

Customizable Architecture Search for Semantic Segmentation

by   Yiheng Zhang, et al.

In this paper, we propose a Customizable Architecture Search (CAS) approach to automatically generate a network architecture for semantic image segmentation. The generated network consists of a sequence of stacked computation cells. A computation cell is represented as a directed acyclic graph, in which each node is a hidden representation (i.e., feature map) and each edge is associated with an operation (e.g., convolution and pooling), which transforms data to a new layer. During the training, the CAS algorithm explores the search space for an optimized computation cell to build a network. The cells of the same type share one architecture but with different weights. In real applications, however, an optimization may need to be conducted under some constraints such as GPU time and model size. To this end, a cost corresponding to the constraint will be assigned to each operation. When an operation is selected during the search, its associated cost will be added to the objective. As a result, our CAS is able to search an optimized architecture with customized constraints. The approach has been thoroughly evaluated on Cityscapes and CamVid datasets, and demonstrates superior performance over several state-of-the-art techniques. More remarkably, our CAS achieves 72.3 mIoU on the Cityscapes dataset with speed of 108 FPS on an Nvidia TitanXp GPU.


page 1

page 2

page 3

page 4


Graph-guided Architecture Search for Real-time Semantic Segmentation

Designing a lightweight semantic segmentation network often requires res...

DOTS: Decoupling Operation and Topology in Differentiable Architecture Search

Differentiable Architecture Search (DARTS) has attracted extensive atten...

Unchain the Search Space with Hierarchical Differentiable Architecture Search

Differentiable architecture search (DAS) has made great progress in sear...

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

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

Stacked BNAS: Rethinking Broad Convolutional Neural Network for Neural Architecture Search

Different from other deep scalable architecture based NAS approaches, Br...

SegNAS3D: Network Architecture Search with Derivative-Free Global Optimization for 3D Image Segmentation

Deep learning has largely reduced the need for manual feature selection ...