Paper ID | IVMSP-5.1 | ||
Paper Title | HOCA: HIGHER-ORDER CHANNEL ATTENTION FOR SINGLE IMAGE SUPER-RESOLUTION | ||
Authors | Yalei Lv, Tao Dai, Bin Chen, Tsinghua University, China; Jian Lu, Shenzhen University, China; Shu-Tao Xia, Tsinghua University, China; Jingchao Cao, City University of Hong Kong, China | ||
Session | IVMSP-5: Super-resolution 1 | ||
Location | Gather.Town | ||
Session Time: | Tuesday, 08 June, 16:30 - 17:15 | ||
Presentation Time: | Tuesday, 08 June, 16:30 - 17:15 | ||
Presentation | Poster | ||
Topic | Image, Video, and Multidimensional Signal Processing: [IVTEC] Image & Video Processing Techniques | ||
IEEE Xplore Open Preview | Click here to view in IEEE Xplore | ||
Abstract | Convolutional neural networks (CNNs) have obtained great success in single image super-resolution (SR). More recent works (e.g., RCAN and SAN) have obtained remarkable performance with channel attention based on first- or second-order statistics of features. However, these methods neglect the rich feature statistics higher than second-order, thus hindering the representation ability of CNNs. To address this issue, we propose a higher-order channel attention (HOCA) module to enhance the representation ability of CNNs. In our HOCA module, to capture different types of semantic information, we first compute k-order of feature statistics, followed by channel attention to learn the feature interdependencies. Considering the diversity of input contents, we design a gate mechanism to adaptively select a specific k-order channel attention. Besides, our HOCA module serves as a plug-and-play module and can be easily plugged into existing state-of-art CNN-based SR methods. Extensive experiments on public benchmarks show that our HOCA module effectively improves the performance of various CNN-based SR methods. |