AutoSegNet: An Automated Neural Network for Image Segmentation
| Autor: | Ni Chen, Edmund Y. Lam, Zhimin Xu, Byoungho Lee, Si Zuo |
|---|---|
| Přispěvatelé: | Department of Communications and Networking, Aalto-yliopisto, Aalto University |
| Rok vydání: | 2020 |
| Předmět: |
General Computer Science
Computer science ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Image processing 02 engineering and technology 01 natural sciences Image (mathematics) 010309 optics Upsampling 0103 physical sciences General Materials Science Segmentation image segmentation Artificial neural network Contextual image classification business.industry deep neural network General Engineering Pattern recognition Image segmentation 021001 nanoscience & nanotechnology Recurrent neural network lcsh:Electrical engineering. Electronics. Nuclear engineering Artificial intelligence 0210 nano-technology business lcsh:TK1-9971 Neural architecture search |
| Zdroj: | IEEE Access, Vol 8, Pp 92452-92461 (2020) |
| ISSN: | 2169-3536 |
| DOI: | 10.1109/access.2020.2995367 |
| Popis: | Neural Architecture Search (NAS) has drawn significant attention as a tool for automatically constructing deep neural networks. The generated neural networks are mainly applied for image classification, and natural language processing. However, there are increasing demands for image segmentation in various areas, such as medical image processing, satellite image object location, and autopilot technology. We propose a NAS method called Automated Segmentation Network (AutoSegNet), targeting industrial and medical image segmentation. The search architectures are constructed by stacking the downsampling layer, the bridge layer, and the upsampling layer, which are explored by a recurrent neural network. Compared with other related methods for image segmentation, the proposed method has a small search space but can explore most of the-state-of-the-art supervised image segmentation models. We perform verification on two datasets, and the results show that AutoSegNet achieves superior segmentation results with clear and continuous segmented edges, as well as better image details. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|