Abstract | ||
---|---|---|
We propose a multi-task end-to-end optimized deep neural network (MEON) for blind image quality assessment (BIQA). MEON consists of two sub-networks-a distortion identification network and a quality prediction network-sharing the early layers. Unlike traditional methods used for training multi-task networks, our training process is performed in two steps. In the first step, we train a distortion t... |
Year | DOI | Venue |
---|---|---|
2018 | 10.1109/TIP.2017.2774045 | IEEE Transactions on Image Processing |
Keywords | Field | DocType |
Training,Image quality,Image coding,Nonlinear distortion,Neural networks | Rectifier (neural networks),Stochastic gradient descent,Normalization (statistics),Pattern recognition,Activation function,Image quality,Artificial intelligence,Nonlinear distortion,Artificial neural network,Distortion,Mathematics | Journal |
Volume | Issue | ISSN |
27 | 3 | 1057-7149 |
Citations | PageRank | References |
53 | 1.19 | 38 |
Authors | ||
6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Kede Ma | 1 | 773 | 27.93 |
Wentao Liu | 2 | 110 | 14.31 |
Kai Zhang | 3 | 686 | 26.59 |
Zhengfang Duanmu | 4 | 171 | 8.24 |
Z Wang | 5 | 13331 | 630.91 |
Wangmeng Zuo | 6 | 3833 | 173.11 |