Searching for Efficient Multi-Scale Architectures for Dense Image Prediction

by   Liang-Chieh Chen, et al.

The design of neural network architectures is an important component for achieving state-of-the-art performance with machine learning systems across a broad array of tasks. Much work has endeavored to design and build architectures automatically through clever construction of a search space paired with simple learning algorithms. Recent progress has demonstrated that such meta-learning methods may exceed scalable human-invented architectures on image classification tasks. An open question is the degree to which such methods may generalize to new domains. In this work we explore the construction of meta-learning techniques for dense image prediction focused on the tasks of scene parsing, person-part segmentation, and semantic image segmentation. Constructing viable search spaces in this domain is challenging because of the multi-scale representation of visual information and the necessity to operate on high resolution imagery. Based on a survey of techniques in dense image prediction, we construct a recursive search space and demonstrate that even with efficient random search, we can identify architectures that outperform human-invented architectures and achieve state-of-the-art performance on three dense prediction tasks including 82.7% on Cityscapes (street scene parsing), 71.3% on PASCAL-Person-Part (person-part segmentation), and 87.9% on PASCAL VOC 2012 (semantic image segmentation). Additionally, the resulting architecture is more computationally efficient, requiring half the parameters and half the computational cost as previous state of the art systems.


page 13

page 14


Auto-DeepLab: Hierarchical Neural Architecture Search for Semantic Image Segmentation

Recently, Neural Architecture Search (NAS) has successfully identified n...

Meta-Learning Initializations for Image Segmentation

While meta-learning approaches that utilize neural network representatio...

DCNAS: Densely Connected Neural Architecture Search for Semantic Image Segmentation

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

Recurrent Segmentation for Variable Computational Budgets

State-of-the-art systems for semantic image segmentation utilize feed-fo...

Pyramidal Convolution: Rethinking Convolutional Neural Networks for Visual Recognition

This work introduces pyramidal convolution (PyConv), which is capable of...

A Survey on Deep Learning Methods for Semantic Image Segmentation in Real-Time

Semantic image segmentation is one of fastest growing areas in computer ...

AIO-P: Expanding Neural Performance Predictors Beyond Image Classification

Evaluating neural network performance is critical to deep neural network...

Please sign up or login with your details

Forgot password? Click here to reset