Correction to: Single Image Super-Resolution via a Holistic Attention Network

By Ben Niu, Weilei Wen, Wenqi Ren, Xiangde Zhang, Lianping Yang, Shuzhen Wang, Kaihao Zhang, Xiaochun Cao, Haifeng Shen. 2020

825 citations recorded by the source corpus.

Informative features play a crucial role in the single image super-resolution task. Channel attention has been demonstrated to be effective for preserving information-rich features in each layer. However, channel attention treats each convolution layer as a separate process that misses the correlation among different layers. To address this problem, we propose a new holistic attention network (HAN), which consists of a layer attention module (LAM) and a channel-spatial attention module (CSAM), to model the holistic interdependencies among layers, channels, and positions. Specifically, the proposed LAM adaptively emphasizes hierarchical features by considering correlations among layers. Meanwhile, CSAM learns the confidence at all the positions of each channel to selectively capture more informative features. Extensive experiments demonstrate that the proposed HAN performs favorably against the state-of-the-art single image super-resolution approaches.

Subfields: Computer Vision and Pattern Recognition

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. Luc Van Gool
2. Radu Timofte
3. Lei Zhang
4. Ming-Hsuan Yang
5. Chen Change Loy
6. Dacheng Tao
7. Kai Zhang
8. Chao Dong

Citations in the corpus

• MAXIM: Multi-Axis MLP for Image Processing (2022, background): “Residual and dense connections [42, 93, 93, 117, 118], the multi-scale feature learning [19,40,95], attention mechanisms [64,89,107,108,118], and non-local networks [52, 91, 118] are such good examples.”
• Dual Aggregation Transformer for Image Super-Resolution (2023, methodology): “We compare our models: DAT-S, DAT-2, and DAT, with state-of-the-art methods: EDSR [14], SRMDNF [27], RDN [32], OISR [9], RCAN [30], NLRN [15], RNAN [31], SRFBN [12], SAN [5], RFANet [16], IGNN [34], HAN [23], CSNLN [22], NLSA [21], CRAN [33], ELAN [29], DFSA [17], SwinIR [13], and CAT-A [4].”
• Activating More Pixels in Image Super-Resolution Transformer (2022, methodology): “By using attention mechanism, [8, 35, 42, 43, 68, 69] achieve further improvement in terms of reconstruction fidelity.”
• TTST: A Top-k Token Selective Transformer for Remote Sensing Image Super-Resolution (2024, methodology): “To comprehensively evaluate the SR performance of our TTST against state-of-the-art methods on remote sensing imagery, we choose both CNN and Transformer-based models for comparison, including EDSR [68], RCAN [38], HAN [39], NLSA [25], HSENet [26], HAUNet [71], TransENet [43], and HAT-L [27].”
• SwinIR: Image Restoration Using Swin Transformer (2021, methodology): “Table 2 shows the quantitative comparisons between SwinIR (middle size) and state-of-the-art methods: DBPN [31], RCAN [95], RRDB [81], SAN [15], IGNN [100], HAN [63], NLSA [61] and IPT [9].”
• Efficient Long-Range Attention Network for Image Super-resolution (2022, methodology): “In addition, to enlarge the receptive field, the CNN-based SR models tend to employ very deep and complicated network topology [60, 10, 64, 41, 40] to recover more details, resulting in much computational resource consumption.”