Channel-Wise and Spatial Feature Modulation Network for Single Image Super-Resolution

By Yanting Hu, Jie Li, Yuanfei Huang, Xinbo Gao. IEEE transactions on circuits and systems for video technology (Print), 2018

294 citations recorded by the source corpus.

The performance of single image super-resolution has achieved significant improvement by utilizing deep convolutional neural networks (CNNs). The features in deep CNN contain different types of information which make different contributions to image reconstruction. However, the most CNN-based models lack discriminative ability for different types of information and deal with them equally, which results in the representational capacity of the models being limited. On the other hand, as the depth of neural network grows, the long-term information coming from preceding layers is easy to be weaken or lost at later layers, which is adverse to super-resolving image. To capture more informative features and maintain long-term information for image super-resolution, we propose a channel-wise and spatial feature modulation (CSFM) network in which a series of feature modulation memory (FMM) modules are cascaded with a densely connected structure to transform shallow features to high informative features. In each FMM module, we construct a set of channel-wise and spatial attention residual (CSAR) blocks and stack them in a chain structure to dynamically modulate the multi-level features in global and local manners. This feature modulation strategy enables the valuable information to be enhanced and the redundant information to be suppressed. Meanwhile, for long-term information persistence, a gated fusion (GF) node is attached at the end of the FMM module to adaptively fuse hierarchical features and distill more effective information via the dense skip connections and the gating mechanism. The extensive quantitative and qualitative evaluations on benchmark datasets illustrate the superiority of our proposed method over the state-of-the-art methods.

Subfields: Computer Vision and Pattern Recognition, Media Technology

View Paper: https://www.semanticscholar.org/paper/c270bcd22083b4846ae824132c16e7c1d7c4e1fa

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Wenqi Ren
2. Xiaochun Cao
3. Hong Liu
4. Juncheng Li
5. Weilei Wen
6. Ben Niu
7. Wenjie Zhang
8. Shuzhen Wang

In Media Technology

1. Wenqi Ren
2. Hong Liu
3. Juncheng Li
4. Xiaochun Cao
5. Weilei Wen
6. Ben Niu
7. Wenjie Zhang
8. Shuzhen Wang

Citations in the corpus

• Correction to: Single Image Super-Resolution via a Holistic Attention Network (2020, background): “In short, they help the network ignore irrelevant information and focus on important information [8,9].”
• Efficient Transformer for Single Image Super-Resolution (2021, background): “To address this issue, numerous deep neural networks have been proposed [1], [2], [3], [4], [5], [6], [7], [8], [9].”
• Residual Feature Aggregation Network for Image Super-Resolution (2020, methodology): “To this end, we design an enhanced spatial attention (ESA) block that is more powerful than the plain one in [10].”