Please use this identifier to cite or link to this item:
https://hdl.handle.net/2440/125724
Citations | ||
Scopus | Web of Science® | Altmetric |
---|---|---|
?
|
?
|
Type: | Journal article |
Title: | RefineNet: multi-path refinement networks for dense prediction |
Author: | Lin, G. Liu, F. Milan, A. Shen, C. Reid, I. |
Citation: | IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020; 42(5):1228-1242 |
Publisher: | IEEE |
Issue Date: | 2020 |
ISSN: | 0162-8828 1939-3539 |
Statement of Responsibility: | Guosheng Lin, Fayao Liu, Anton Milan, Chunhua Shen, and Ian Reid |
Abstract: | Recently, very deep convolutional neural networks (CNNs) have shown outstanding performance in object recognition and have also been the first choice for dense prediction problems such as semantic segmentation and depth estimation. However, repeated subsampling operations like pooling or convolution striding in deep CNNs lead to a significant decrease in the initial image resolution. Here, we present RefineNet, a generic multi-path refinement network that explicitly exploits all the information available along the down-sampling process to enable high-resolution prediction using long-range residual connections. In this way, the deeper layers that capture high-level semantic features can be directly refined using fine-grained features from earlier convolutions. The individual components of RefineNet employ residual connections following the identity mapping mindset, which allows for effective end-to-end training. Further, we introduce chained residual pooling, which captures rich background context in an efficient manner. We carry out comprehensive experiments on semantic segmentation which is a dense classification problem and achieve good performance on seven public datasets. We further apply our method for depth estimation and demonstrate the effectiveness of our method on dense regression problems. |
Keywords: | Convolutional neural network; semantic segmentation; object parsing; human parsing; scene parsing; depth estimation; dense prediction |
Rights: | © 2019 IEEE. Personal use is permitted, but republication/redistribution requires IEEE permission. See https://www.ieee.org/publications/rights/index.html for more information. |
DOI: | 10.1109/TPAMI.2019.2893630 |
Grant ID: | http://purl.org/au-research/grants/arc/CE140100016 http://purl.org/au-research/grants/arc/FT120100969 http://purl.org/au-research/grants/arc/FL130100102 |
Published version: | http://dx.doi.org/10.1109/tpami.2019.2893630 |
Appears in Collections: | Aurora harvest 8 Computer Science publications |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
hdl_125724.pdf | Accepted version | 8.62 MB | Adobe PDF | View/Open |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.