Paper Info
Title
Auto-DeepLab: Hierarchical Neural Architecture Search for Semantic Image Segmentation
Abstract
Recently, Neural Architecture Search (NAS) has successfully identified neural network architectures that exceed human designed ones on large-scale image classification. In this paper, we study NAS for semantic image segmentation. Existing works often focus on searching the repeatable cell structure, while hand-designing the outer network structure that controls the spatial resolution changes. This choice simplifies the search space, but becomes increasingly problematic for dense image prediction which exhibits a lot more network level architectural variations. Therefore, we propose to search the network level structure in addition to the cell level structure, which forms a hierarchical architecture search space. We present a network level search space that includes many popular designs, and develop a formulation that allows efficient gradient-based architecture search (3 P100 GPU days on Cityscapes images). We demonstrate the effectiveness of the proposed method on the challenging Cityscapes, PASCAL VOC 2012, and ADE20K datasets. Auto-DeepLab, our architecture searched specifically for semantic image segmentation, attains state-of-the-art performance without any ImageNet pretraining.
Year
DOI
Venue
2019
10.1109/CVPR.2019.00017
2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Keywords
Field
DocType
Deep Learning,Segmentation,Grouping and Shape
Network level,Architecture,Pattern recognition,Computer science,Level structure,Semantic image segmentation,Artificial intelligence,Contextual image classification,Artificial neural network,Image resolution,Network structure
Journal
Volume
ISSN
ISBN
abs/1901.02985
1063-6919
978-1-7281-3294-5
Citations 
PageRank 
References 
73
1.43
54
Authors
7
Name
Order
Citations
PageRank
Chenxi Liu11275.38
Liang-Chieh Chen2227277.92
Florian Schroff375732.72
Hartwig Adam4132642.50
Wei Hua5731.43
Alan L. Yuille6103391902.01
Li Fei-Fei7224831135.90