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.

To appear in CVPR 2019 as oral. Code for Auto-DeepLab released at https://github.com/tensorflow/models/tree/master/research/deeplab

References in corpus (7)

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Sequence to Sequence Learning with Neural Networks
• Rethinking Atrous Convolution for Semantic Image Segmentation
• Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation
• Designing Neural Network Architectures using Reinforcement Learning
• Efficient Architecture Search by Network Transformation
• Stacked Deconvolutional Network for Semantic Segmentation

Cited by in corpus (25)

• Hierarchical Neural Architecture Search for Deep Stereo Matching
• A Survey on Neural Architecture Search
• Polarized Self-Attention: Towards High-quality Pixel-wise Regression
• Progressive Differentiable Architecture Search: Bridging the Depth Gap between Search and Evaluation
• Gated-SCNN: Gated Shape CNNs for Semantic Segmentation
• Learning Graph Convolutional Network for Skeleton-based Human Action Recognition by Neural Searching
• Trilevel Neural Architecture Search for Efficient Single Image Super-Resolution
• SM-NAS: Structural-to-Modular Neural Architecture Search for Object Detection
• Neural Architecture Search for Deep Face Recognition
• ObjectAug: Object-level Data Augmentation for Semantic Image Segmentation
• Towards Oracle Knowledge Distillation with Neural Architecture Search
• Video Action Recognition Via Neural Architecture Searching
• Modeling Neural Architecture Search Methods for Deep Networks
• Searching for Stage-wise Neural Graphs In the Limit
• Rethinking Performance Estimation in Neural Architecture Search
• Joint-DetNAS: Upgrade Your Detector with NAS, Pruning and Dynamic Distillation
• Progressive Neural Index Search for Database System
• A deep learning based multiscale approach to segment cancer area in liver whole slide image
• Neural Architecture Search for Gliomas Segmentation on Multimodal Magnetic Resonance Imaging
• WAS-VTON: Warping Architecture Search for Virtual Try-on Network
• UXNet: Searching Multi-level Feature Aggregation for 3D Medical Image Segmentation
• Neural Architecture Search for Image Super-Resolution Using Densely Constructed Search Space: DeCoNAS
• Searching Learning Strategy with Reinforcement Learning for 3D Medical Image Segmentation
• LV-BERT: Exploiting Layer Variety for BERT
• Efficient Data-specific Model Search for Collaborative Filtering