期刊
IEEE TRANSACTIONS ON IMAGE PROCESSING
卷 25, 期 5, 页码 2117-2129出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TIP.2016.2541318
关键词
Non-local auto-encoder; network stabilization; image restoration
资金
- Australian Research Council [DP-140102164, LE140100061, FT-130101457]
- Australian Research Council [LE140100061] Funding Source: Australian Research Council
Deep neural networks have been applied to image restoration to achieve the top-level performance. From a neuroscience perspective, the layerwise abstraction of knowledge in a deep neural network can, to some extent, reveal the mechanisms of how visual cues are processed in human brain. A pivotal property of human brain is that similar visual cues can stimulate the same neuron to induce similar neurological signals. However, conventional neural networks do not consider this property, and the resulting models are, as a result, unstable regarding their internal propagation. In this paper, we develop the (stacked) non-local auto-encoder, which exploits self-similar information in natural images for stability. We propose that similar inputs should induce similar network propagation. This is achieved by constraining the difference between the hidden representations of non-local similar image blocks during training. By applying the proposed model to image restoration, we then develop a collaborative stabilization step to further rectify forward propagation. To obtain a reliable deep model, we employ several strategies to simplify training and improve testing. Extensive image restoration experiments, including image denoising and super-resolution, demonstrate the effectiveness of the proposed method.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据