Searching for Efficient Multi-Scale Architectures for Dense Image Prediction

TL;DR

This paper develops a meta-learning based neural architecture search method for dense image prediction tasks, achieving state-of-the-art results with more efficient models that outperform human-designed architectures.

Contribution

It introduces a recursive search space tailored for dense prediction, demonstrating that random search can find architectures surpassing human designs in accuracy and efficiency.

Findings

Achieved 82.7% on Cityscapes for street scene parsing.

Achieved 71.3% on PASCAL-Person-Part for person-part segmentation.

Achieved 87.9% on PASCAL VOC 2012 for semantic segmentation.

Abstract

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.