Name
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. |
Year | Venue | Keywords |
|---|---|---|
2018 | ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 31 (NIPS 2018) | computationally efficient,computational cost,learning algorithms,search space,logarithmic growth,a survey |
DocType | Volume | ISSN |
Conference | 31 | 1049-5258 |
Citations | PageRank | References |
26 | 0.77 | 53 |
Authors | ||
8 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Liang-Chieh Chen | 1 | 2272 | 77.92 |
| Maxwell D. Collins | 2 | 33 | 2.23 |
| Yukun Zhu | 3 | 764 | 30.85 |
| George Papandreou | 4 | 2115 | 76.08 |
| Barret Zoph | 5 | 729 | 21.33 |
| Florian Schroff | 6 | 757 | 32.72 |
| Hartwig Adam | 7 | 1326 | 42.50 |
| Jonathon Shlens | 8 | 3851 | 153.79 |