Lightweight image super-resolution reconstruction based on asymmetric information distillation network

doi:10.11772/j.issn.1001-9081.2024030276

Abstract

Abstract:

Deep Convolutional Neural Network （CNN） has impressive performance in image super-resolution reconstruction. However， many current related methods have a lot of model parameters， making them unsuitable for devices with limited computational resources. To address the above problem， a lightweight Asymmetric Information Distillation Network （AIDN） was proposed. Firstly， effective feature information was extracted from the input original images and edge images. Secondly， an asymmetric information distillation module was designed for non-linear mapping learning on these features. Thirdly， multiple residual images were reconstructed by an upsampling module and fused into one residual image through attention mechanism. Finally， the fused residual image was added to the interpolation of the input image to generate the super-resolution image. Experimental results on Set14， Urban100， and Manga109 datasets show that the 4× super-resolution Peak Signal-to-Noise Ratio （PSNR） values of AIDN model are improved by 0.03 dB， 0.14 dB， and 0.06 dB， respectively， compared to those of Spatial Adaptive Feature Modulation Network （SAFMN）. This demonstrates that AIDN model achieves a superior balance between model parameters and performance.

Key words: image super-resolution, lightweight super-resolution network, asymmetric convolution, information distillation, attention mechanism

摘要：

深度卷积神经网络（CNN）在图像超分辨率重建领域表现出卓越性能，然而现有的许多相关方法的模型参数量较多，无法应用至计算资源较低的设备。为缓解上述问题，提出一个轻量级的非对称信息蒸馏网络（AIDN）模型。首先，输入原始图像及其边缘图像以提取有效的特征信息；其次，设计一个非对称信息蒸馏块对提取到的特征进行非线性映射学习；再次，使用上采样模块重建多个残差图像后，将这些残差图像经过注意力机制融合成一个残差图像；最后，将融合的残差图像与输入图像的插值相加后得到超分图像。在Set14、Urban100和Manga109数据集上的实验结果表明，相较于空间自适应特征调制网络（SAFMN），AIDN模型的4倍超分峰值信噪比（PSNR）值分别提升了0.03 dB、0.14 dB和0.06 dB，说明了AIDN模型在模型参数量和模型性能之间取得了更好的平衡。

关键词: 图像超分辨率, 轻量级超分辨率网络, 非对称卷积, 信息蒸馏, 注意力机制

CLC Number:

TP391.4

Haiteng MENG, Xiaole ZHAO, Tianrui LI. Lightweight image super-resolution reconstruction based on asymmetric information distillation network[J]. Journal of Computer Applications, 2025, 45(2): 601-609.

孟海腾, 赵小乐, 李天瑞. 基于非对称信息蒸馏网络的轻量级图像超分辨重建[J]. 《计算机应用》唯一官方网站, 2025, 45(2): 601-609.

Figures/Tables 20

Fig. 1 Overall structure of asymmetric information distillation network

Fig. 2 Structure of shallow feature extraction module

Fig. 3 Structure of asymmetric information distillation block

Fig. 4 Structures of ESA module and IESA module

Fig. 5 Structure of upsampling module

Fig. 6 Structures of U module under different super-resolution multiples

Fig. 7 Structure of attention selection module

Tab. 1 Detailed experimental parameters of AIDN model

模块名	输出特征大小	子模块名	子模块结构
SFEM	64×64	Conv3	3×3，3
SFEM	64×64	Conv3	｛3×3，26｝×2
AIDB	64×64	HvConv	$1 × 3 32 3 × 1 32$ ×4
		VhConv	$3 × 1 20 1 × 3 20$ ×4
		Conv1	｛1×1，26｝×4
		Conv1	1×1，52
IESA	64×64	Conv1	1×1，13
	31×31	Strided Conv	3×3，13，s=2
	15×15	Pooling	2×2，s=2
	64×64	DwConv3	3×3，13，g=13
	31×31	DwConv3	3×3，13，g=13
	15×15	DwConv3	3×3，13，g=13
	64×64	Conv1	1×1，52
UM	64×64	Conv3（U）	3×3，3r²
UM	$64 n × 64 n$	Conv3	3×3，3
ASM	$64 n × 64 n$	Conv1	1×1，24
		Conv1×3	1×3，24
		Conv3×1	3×1，24
		Conv1	1×1，12

Tab. 1 Detailed experimental parameters of AIDN model

模块名	输出特征大小	子模块名	子模块结构
SFEM	64×64	Conv3	3×3，3
SFEM	64×64	Conv3	｛3×3，26｝×2
AIDB	64×64	HvConv	$1 × 3 32 3 × 1 32$ ×4
		VhConv	$3 × 1 20 1 × 3 20$ ×4
		Conv1	｛1×1，26｝×4
		Conv1	1×1，52
IESA	64×64	Conv1	1×1，13
	31×31	Strided Conv	3×3，13，s=2
	15×15	Pooling	2×2，s=2
	64×64	DwConv3	3×3，13，g=13
	31×31	DwConv3	3×3，13，g=13
	15×15	DwConv3	3×3，13，g=13
	64×64	Conv1	1×1，52
UM	64×64	Conv3（U）	3×3，3r²
UM	$64 n × 64 n$	Conv3	3×3，3
ASM	$64 n × 64 n$	Conv1	1×1，24
		Conv1×3	1×3，24
		Conv3×1	3×1，24
		Conv1	1×1，12

Tab. 2 Comparison of 2× results of different super-resolution networks on 5 benchmark datasets

模型名	参数量/ $103$	Set5		Set14		B100		Urban100		Manga109
模型名	参数量/ $103$	PSNR/dB	SSIM	PSNR/dB	SSIM	PSNR/dB	SSIM	PSNR/dB	SSIM	PSNR/dB	SSIM
Bicubic	—	33.66	0.929 9	30.24	0.868 8	29.56	0.843 1	26.88	0.840 3	30.80	0.933 9
SRCNN^［1］	57	36.66	0.954 2	32.45	0.906 7	31.36	0.887 9	29.50	0.894 6	35.60	0.966 3
FSRCNN^［8］	12	37.00	0.955 8	32.63	0.908 8	31.53	0.892 0	29.88	0.902 0	36.67	0.971 0
LapSRN^［17］	813	37.52	0.959 1	33.08	0.913 0	31.08	0.895 0	30.42	0.910 1	37.27	0.974 0
MemNet^［33］	677	37.78	0.959 7	33.28	0.914 2	32.08	0.897 8	31.31	0.919 5	37.72	0.974 0
IDN^［4］	553	37.83	0.960 0	33.30	0.914 8	32.08	0.898 5	31.27	0.919 6	38.01	0.974 9
IMDN^［15］	694	38.00	0.960 5	33.63	0.917 7	32.19	0.899 6	32.17	0.928 3	38.88	0.977 4
PAN^［19］	261	38.00	0.960 5	33.59	0.918 1	32.18	0.899 7	32.01	0.927 3	38.70	0.977 3
ShuffleMixer^［34］	394	38.01	0.960 6	33.63	0.918 0	32.17	0.899 5	31.89	0.925 7	38.83	0.977 4
SAFMN^［21］	228	38.00	0.960 5	33.54	0.917 7	32.16	0.899 5	31.84	0.925 6	38.71	0.977 1
AIDN（本文）	229	38.02	0.960 4	33.55	0.917 7	32.18	0.899 7	32.02	0.927 1	38.77	0.977 3

Tab. 2 Comparison of 2× results of different super-resolution networks on 5 benchmark datasets

模型名	参数量/ $103$	Set5		Set14		B100		Urban100		Manga109
模型名	参数量/ $103$	PSNR/dB	SSIM	PSNR/dB	SSIM	PSNR/dB	SSIM	PSNR/dB	SSIM	PSNR/dB	SSIM
Bicubic	—	33.66	0.929 9	30.24	0.868 8	29.56	0.843 1	26.88	0.840 3	30.80	0.933 9
SRCNN^［1］	57	36.66	0.954 2	32.45	0.906 7	31.36	0.887 9	29.50	0.894 6	35.60	0.966 3
FSRCNN^［8］	12	37.00	0.955 8	32.63	0.908 8	31.53	0.892 0	29.88	0.902 0	36.67	0.971 0
LapSRN^［17］	813	37.52	0.959 1	33.08	0.913 0	31.08	0.895 0	30.42	0.910 1	37.27	0.974 0
MemNet^［33］	677	37.78	0.959 7	33.28	0.914 2	32.08	0.897 8	31.31	0.919 5	37.72	0.974 0
IDN^［4］	553	37.83	0.960 0	33.30	0.914 8	32.08	0.898 5	31.27	0.919 6	38.01	0.974 9
IMDN^［15］	694	38.00	0.960 5	33.63	0.917 7	32.19	0.899 6	32.17	0.928 3	38.88	0.977 4
PAN^［19］	261	38.00	0.960 5	33.59	0.918 1	32.18	0.899 7	32.01	0.927 3	38.70	0.977 3
ShuffleMixer^［34］	394	38.01	0.960 6	33.63	0.918 0	32.17	0.899 5	31.89	0.925 7	38.83	0.977 4
SAFMN^［21］	228	38.00	0.960 5	33.54	0.917 7	32.16	0.899 5	31.84	0.925 6	38.71	0.977 1
AIDN（本文）	229	38.02	0.960 4	33.55	0.917 7	32.18	0.899 7	32.02	0.927 1	38.77	0.977 3

Tab. 3 Comparison of 3× results of different super-resolution networks on 5 benchmark datasets

模型名	参数量/ $103$	Set5		Set14		B100		Urban100		Manga109
模型名	参数量/ $103$	PSNR/dB	SSIM	PSNR/dB	SSIM	PSNR/dB	SSIM	PSNR/dB	SSIM	PSNR/dB	SSIM
Bicubic	—	30.39	0.868 2	27.55	0.774 2	27.21	0.738 5	24.46	0.734 9	26.95	0.855 6
SRCNN^［1］	57	32.75	0.909 0	29.28	0.820 9	28.41	0.786 3	26.24	0.798 9	30.69	0.917 0
FSRCNN^［8］	12	33.16	0.914 0	29.43	0.824 2	28.53	0.791 0	26.43	0.808 0	30.98	0.921 2
MemNet^［33］	677	34.09	0.924 8	30.01	0.835 0	28.96	0.800 1	27.56	0.837 6	32.51	0.936 9
IDN^［4］	553	34.11	0.925 3	29.99	0.835 4	28.95	0.801 3	27.42	0.835 9	32.71	0.938 1
IMDN^［15］	703	34.36	0.927 0	30.32	0.841 7	29.09	0.804 6	27.17	0.851 9	33.61	0.944 5
PAN^［19］	261	34.40	0.927 2	30.37	0.842 3	29.12	0.805 1	28.08	0.849 8	33.69	0.944 8
ShuffleMixer^［34］	415	34.40	0.927 2	30.37	0.842 3	29.12	0.805 1	28.08	0.849 8	33.69	0.944 8
SAFMN^［21］	233	34.34	0.936 7	30.33	0.841 8	29.08	0.804 8	27.95	0.847 4	33.52	0.943 7
AIDN（本文）	257	34.42	0.927 3	30.36	0.842 4	29.12	0.805 2	28.16	0.852 4	33.66	0.844 9

Tab. 3 Comparison of 3× results of different super-resolution networks on 5 benchmark datasets

模型名	参数量/ $103$	Set5		Set14		B100		Urban100		Manga109
模型名	参数量/ $103$	PSNR/dB	SSIM	PSNR/dB	SSIM	PSNR/dB	SSIM	PSNR/dB	SSIM	PSNR/dB	SSIM
Bicubic	—	30.39	0.868 2	27.55	0.774 2	27.21	0.738 5	24.46	0.734 9	26.95	0.855 6
SRCNN^［1］	57	32.75	0.909 0	29.28	0.820 9	28.41	0.786 3	26.24	0.798 9	30.69	0.917 0
FSRCNN^［8］	12	33.16	0.914 0	29.43	0.824 2	28.53	0.791 0	26.43	0.808 0	30.98	0.921 2
MemNet^［33］	677	34.09	0.924 8	30.01	0.835 0	28.96	0.800 1	27.56	0.837 6	32.51	0.936 9
IDN^［4］	553	34.11	0.925 3	29.99	0.835 4	28.95	0.801 3	27.42	0.835 9	32.71	0.938 1
IMDN^［15］	703	34.36	0.927 0	30.32	0.841 7	29.09	0.804 6	27.17	0.851 9	33.61	0.944 5
PAN^［19］	261	34.40	0.927 2	30.37	0.842 3	29.12	0.805 1	28.08	0.849 8	33.69	0.944 8
ShuffleMixer^［34］	415	34.40	0.927 2	30.37	0.842 3	29.12	0.805 1	28.08	0.849 8	33.69	0.944 8
SAFMN^［21］	233	34.34	0.936 7	30.33	0.841 8	29.08	0.804 8	27.95	0.847 4	33.52	0.943 7
AIDN（本文）	257	34.42	0.927 3	30.36	0.842 4	29.12	0.805 2	28.16	0.852 4	33.66	0.844 9

Tab. 4 Comparison of 4× results of different super-resolution networks on 5 benchmark datasets

模型名	参数量/ $103$	Set5		Set14		B100		Urban100		Manga109
模型名	参数量/ $103$	PSNR/dB	SSIM	PSNR/dB	SSIM	PSNR/dB	SSIM	PSNR/dB	SSIM	PSNR/dB	SSIM
Bicubic	—	28.42	0.810 4	26.00	0.702 7	25.96	0.667 5	23.14	0.657 7	24.89	0.786 6
SRCNN^［1］	57	30.48	0.862 8	27.49	0.750 3	26.90	0.710 1	24.52	0.722 1	27.66	0.850 5
FSRCNN^［8］	12	30.71	0.865 7	27.59	0.753 5	26.98	0.715 0	24.62	0.828 0	27.90	0.851 7
LapSRN^［17］	813	31.54	0.885 0	28.19	0.772 0	27.32	0.728 0	25.21	0.756 0	29.09	0.884 5
MemNet^［33］	677	31.74	0.889 3	28.26	0.772 3	27.40	0.728 1	25.50	0.763 0	29.42	0.894 2
IDN^［4］	553	31.82	0.890 3	28.25	0.773 0	27.41	0.729 7	25.41	0.763 2	29.41	0.894 2
IMDN^［15］	715	32.21	0.894 8	28.58	0.781 1	27.56	0.735 3	26.04	0.783 8	30.45	0.907 5
PAN^［19］	261	32.13	0.894 8	28.66	0.782 7	27.61	0.736 6	26.08	0.783 5	30.65	0.909 3
HPUN-S^［35］	246	32.09	0.893 1	28.52	0.779 7	27.54	0.734 8	25.86	0.778 8	30.21	0.904 3
ShuffleMixer^［34］	411	32.21	0.895 3	28.66	0.782 7	27.61	0.736 6	26.08	0.783 5	30.65	0.909 3
SAFMN^［21］	240	32.18	0.894 8	28.60	0.781 3	27.58	0.735 9	25.97	0.780 9	30.43	0.909 3
AIDN（本文）	229	32.18	0.894 6	28.63	0.787 1	27.58	0.735 9	26.11	0.785 8	30.49	0.908 5

Tab. 4 Comparison of 4× results of different super-resolution networks on 5 benchmark datasets

模型名	参数量/ $103$	Set5		Set14		B100		Urban100		Manga109
模型名	参数量/ $103$	PSNR/dB	SSIM	PSNR/dB	SSIM	PSNR/dB	SSIM	PSNR/dB	SSIM	PSNR/dB	SSIM
Bicubic	—	28.42	0.810 4	26.00	0.702 7	25.96	0.667 5	23.14	0.657 7	24.89	0.786 6
SRCNN^［1］	57	30.48	0.862 8	27.49	0.750 3	26.90	0.710 1	24.52	0.722 1	27.66	0.850 5
FSRCNN^［8］	12	30.71	0.865 7	27.59	0.753 5	26.98	0.715 0	24.62	0.828 0	27.90	0.851 7
LapSRN^［17］	813	31.54	0.885 0	28.19	0.772 0	27.32	0.728 0	25.21	0.756 0	29.09	0.884 5
MemNet^［33］	677	31.74	0.889 3	28.26	0.772 3	27.40	0.728 1	25.50	0.763 0	29.42	0.894 2
IDN^［4］	553	31.82	0.890 3	28.25	0.773 0	27.41	0.729 7	25.41	0.763 2	29.41	0.894 2
IMDN^［15］	715	32.21	0.894 8	28.58	0.781 1	27.56	0.735 3	26.04	0.783 8	30.45	0.907 5
PAN^［19］	261	32.13	0.894 8	28.66	0.782 7	27.61	0.736 6	26.08	0.783 5	30.65	0.909 3
HPUN-S^［35］	246	32.09	0.893 1	28.52	0.779 7	27.54	0.734 8	25.86	0.778 8	30.21	0.904 3
ShuffleMixer^［34］	411	32.21	0.895 3	28.66	0.782 7	27.61	0.736 6	26.08	0.783 5	30.65	0.909 3
SAFMN^［21］	240	32.18	0.894 8	28.60	0.781 3	27.58	0.735 9	25.97	0.780 9	30.43	0.909 3
AIDN（本文）	229	32.18	0.894 6	28.63	0.787 1	27.58	0.735 9	26.11	0.785 8	30.49	0.908 5

Fig. 8 Comparison of model parameters and performance of AIDN and other lightweight algorithms

Fig. 9 Comparison of 4× super-resolution visual results of different algorithms

Fig. 10 Visualization of images and features at each stage of shallow feature extraction module

Tab. 5 Experimental results of 4x super-resolution ablation of AIDN on Set5 dataset

实验序号	实验设置				模型参数量	PSNR/dB
实验序号	ESA	IESA	edge	ASM	模型参数量	PSNR/dB
1	√	×	×	×	237 491	31.51
2	×	√	×	×	225 323	31.55
3	×	√	√	×	225 404	31.56
4	×	√	×	√	229 439	32.10
5	×	√	√	√	229 520	32.11

Fig. 11 Convergence curves of ESA， IESA， ASM and edge modules

Fig. 12 Comparison of schematic diagram betweentwo intermediate feature processing methods

Fig. 13 Training convergence curves of different intermediate feature processing methods

Fig. 14 Visual comparison of example feature maps output by each module of m1 and m3

Fig. 15 Failure case of AIDN for image super-resolution

References 36

1	DONG C， LOY C C， HE K， et al. Learning a deep convolutional network for image super-resolution［C］// Proceedings of the 2014 European Conference on Computer Vision， LNCS 8692. Cham： Springer， 2014： 184-199.
2	KIM J， LEE J K， LEE K M. Accurate image super-resolution using very deep convolutional networks［C］// Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE， 2016： 1646-1654.
3	KIM J， LEE J K， LEE K M. Deeply-recursive convolutional network for image super-resolution［C］// Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE， 2016： 1637-1645.
4	ZHENG H， WANG X， GAO X. Fast and accurate single image super-resolution via information distillation network［C］// Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE， 2018： 723-731.
5	SZEGEDY C， VANHOUCKE V， LOFFE S， et al. Rethinking the inception architecture for computer vision［C］// Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE， 2016： 2818-2826.
6	TIAN C， XU Y， ZUO W， et al. Asymmetric CNN for image super-resolution［J］. IEEE Transactions on Systems， Man， and Cybernetics： Systems， 2022， 52（6）： 3718-3730.
7	ZONG Z， ZHA L， JIANG J， et al. Asymmetric information distillation network for lightweight super resolution［C］// Proceedings of the 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops. Piscataway： IEEE， 2022： 1248-1257.
8	DONG C， LOY C C， TANG X. Accelerating the super-resolution convolutional neural network［C］// Proceedings of the 2016 European Conference on Computer Vision， LNCS 9906. Cham： Springer， 2016： 391-407.
9	LIM B， SON S， KIM H， et al. Enhanced deep residual networks for single image super-resolution［C］// Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops. Piscataway： IEEE， 2017： 1132-1140.
10	ZHANG Y， LI K， LI K， et al. Image super-resolution using very deep residual channel attention networks［C］// Proceedings of the 2018 European Conference on Computer Vision， LNCS 11211. Cham： Springer， 2018： 294-310.
11	DOSOVITSKIY A， BEYER L， KOLESNIKOV A， et al. An image is worth 16×16 words： transformers for image recognition at scale［EB/OL］. ［2024-01-13］..
12	LIANG J， CAO J， SUN G， et al. SwinIR： image restoration using Swin Transformer［C］// Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision Workshops. Piscataway： IEEE， 2021： 1833-1844.
13	ZHANG X， ZENG H， GUO S， et al. Efficient long-range attention network for image super resolution［C］// Proceedings of the 2022 European Conference on Computer Vision， LNCS 13677. Cham： Springer， 2022： 649-667.
14	ZHOU Y， LI Z， GUO C L， et al. SRFormer： permuted self-attention for single image super-resolution［C］// Proceedings of the 2023 IEEE/CVF International Conference on Computer Vision. Piscataway： IEEE， 2023： 12734-12745.
15	ZHENG H， GAO X， YANG Y， et al. Lightweight image super-resolution with information multi-distillation network［C］// Proceedings of the 27th ACM International Conference on Multimedia. New York： ACM， 2019： 2024-2032.
16	LIU J， TANG J， WU G. Residual feature distillation network for lightweight image super-resolution［C］// Proceedings of the 2020 European Conference on Computer Vision Workshops， LNCS 12537. Cham： Springer， 2020： 41-55.
17	LAI W S， HUANG J B， AHUJA N， et al. Deep Laplacian pyramid networks for fast and accurate super-resolution［C］// Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE， 2017： 5835-5843.
18	LAI W S， HUANG J B， AHUJA N， et al. Fast and accurate image super-resolution with deep Laplacian pyramid networks［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence， 2019， 41（11）： 2599-2613.
19	ZHAO H， KONG X， HE J， et al. Efficient image super-resolution using pixel attention［C］// Proceedings of the 2020 European Conference on Computer Vision Workshops， LNCS 12537. Cham： Springer， 2020： 56-72.
20	LI Z， LIU Y， CHEN X， et al. Blueprint separable residual network for efficient image super-resolution［C］// Proceedings of the 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops. Piscataway： IEEE， 2022： 832-842.
21	SUN L， DONG J， TANG J， et al. Spatially-adaptive feature modulation for efficient image super-resolution［C］// Proceedings of the 2023 IEEE/CVF International Conference on Computer Vision. Piscataway： IEEE， 2023： 13144-13153.
22	FANG J， LIN H， CHEN X， et al. A hybrid network of CNN and Transformer for lightweight image super-resolution［C］// Proceedings of the 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops. Piscataway： IEEE， 2022： 1102-1111.
23	ZHANG A， REN W， LIU Y， et al. Lightweight image super-resolution with super-pixel token interaction［C］// Proceedings of the 2023 IEEE/CVF International Conference on Computer Vision. Piscataway： IEEE， 2023： 12682-12691.
24	HU J， SHEN L， SUN G. Squeeze-and-excitation networks［C］// Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE， 2018： 7132-7141.
25	LIU J， ZHANG W， TANG Y， et al. Residual feature aggregation network for image super-resolution［C］// Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE， 2020： 2356-2365.
26	KONG F， LI M， LIU S， et al. Residual local feature network for efficient super-resolution［C］// Proceedings of the 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops. Piscataway： IEEE， 2022： 765-775.
27	TIMOFTE R， AGUSTSSON E， VAN GOOL L， et al. NTIRE 2017 challenge on single image super-resolution： methods and results［C］// Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops. Piscataway： IEEE， 2017： 1110-1121.
28	BEVILACQUA M， ROUMY A， GUILLEMOT C， et al. Low-complexity single-image super-resolution based on nonnegative neighbor embedding［C］// Proceedings of the 2012 British Machine Vision Conference. Durham： BMVA Press， 2012： 1-10.
29	ZEYDE R， ELAD M， PROTTER M. On single image scale-up using sparse-representations［C］// Proceedings of the 2010 International Conference on Curves and Surfaces， LNCS 6920. Berlin： Springer， 2012： 711-730.
30	MARTIN D， FOWLKES C， TAL D， et al. A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics［C］// Proceedings of the 8th IEEE International Conference on Computer Vision. Piscataway： IEEE， 2001： 416-423.
31	HUANG J B， SINGH A， AHUJA N. Single image super-resolution from transformed self-exemplars［C］// Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE， 2015： 5197-5206.
32	MATSUI Y， ITO K， ARAMAKI Y， et al. Sketch-based manga retrieval using manga109 dataset［J］. Multimedia Tools and Applications， 2017， 76（20）： 21811-21838.
33	TAI Y， YANG J， LIU X， et al. MemNet： a persistent memory network for image restoration［C］// Proceedings of the 2017 IEEE International Conference on Computer Vision. Piscataway： IEEE， 2017： 4549-4557.
34	SUN L， PAN J， TANG J. ShuffleMixer： an efficient ConvNet for image super-resolution［C］// Proceedings of the 36th International Conference on Neural Information Processing Systems. Red Hook： Curran Associates Inc.， 2022： 17314-17326.
35	SUN B， ZHANG Y， JIANG S， et al. Hybrid pixel-unshuffled network for lightweight image super-resolution［C］// Proceedings of the 2023 AAAI Conference on Artificial Intelligence. Palo Alto： AAAI Press， 2023： 2375-2383.
36	AHN N， KANG B， SOHN K A. Fast， accurate， and lightweight super-resolution with cascading residual network［C］// Proceedings of the 2018 European Conference on Computer Vision， LNCS 11214. Cham： Springer， 2018： 256-272.

[1]	Qijian CAI, Wei TAN. Semantic graph enhanced multi-modal recommendation algorithm [J]. Journal of Computer Applications, 2025, 45(2): 421-427.
[2]	Dixin WANG, Jiahao WANG, Min LI, Hao CHEN, Guangyao HU, Yu GONG. Abnormal attack detection for underwater acoustic communication network [J]. Journal of Computer Applications, 2025, 45(2): 526-533.
[3]	Jialin ZHANG, Qinghua REN, Qirong MAO. Speaker verification system utilizing global-local feature dependency for anti-spoofing [J]. Journal of Computer Applications, 2025, 45(1): 308-317.
[4]	Ying HUANG, Changsheng LI, Hui PENG, Su LIU. Dual-branch network guided by local entropy for dynamic scene high dynamic range imaging [J]. Journal of Computer Applications, 2025, 45(1): 204-213.
[5]	Lifang WANG, Jingshuang WU, Pengliang YIN, Lihua HU. Action recognition algorithm based on attention mechanism and energy function [J]. Journal of Computer Applications, 2025, 45(1): 234-239.
[6]	Jie XU, Yong ZHONG, Yang WANG, Changfu ZHANG, Guanci YANG. Facial attribute estimation and expression recognition based on contextual channel attention mechanism [J]. Journal of Computer Applications, 2025, 45(1): 253-260.
[7]	Junying CHEN, Shijie GUO, Lingling CHEN. Lightweight human pose estimation based on decoupled attention and ghost convolution [J]. Journal of Computer Applications, 2025, 45(1): 223-233.
[8]	Liting LI, Bei HUA, Ruozhou HE, Kuang XU. Multivariate time series prediction model based on decoupled attention mechanism [J]. Journal of Computer Applications, 2024, 44(9): 2732-2738.
[9]	Zhiqiang ZHAO, Peihong MA, Xinhong HEI. Crowd counting method based on dual attention mechanism [J]. Journal of Computer Applications, 2024, 44(9): 2886-2892.
[10]	Jing QIN, Zhiguang QIN, Fali LI, Yueheng PENG. Diagnosis of major depressive disorder based on probabilistic sparse self-attention neural network [J]. Journal of Computer Applications, 2024, 44(9): 2970-2974.
[11]	Zhonghua LI, Yunqi BAI, Xuejin WANG, Leilei HUANG, Chujun LIN, Shiyu LIAO. Low illumination face detection based on image enhancement [J]. Journal of Computer Applications, 2024, 44(8): 2588-2594.
[12]	Shangbin MO, Wenjun WANG, Ling DONG, Shengxiang GAO, Zhengtao YU. Single-channel speech enhancement based on multi-channel information aggregation and collaborative decoding [J]. Journal of Computer Applications, 2024, 44(8): 2611-2617.
[13]	Kaipeng XUE, Tao XU, Chunjie LIAO. Multimodal sentiment analysis network with self-supervision and multi-layer cross attention [J]. Journal of Computer Applications, 2024, 44(8): 2387-2392.
[14]	Pengqi GAO, Heming HUANG, Yonghong FAN. Fusion of coordinate and multi-head attention mechanisms for interactive speech emotion recognition [J]. Journal of Computer Applications, 2024, 44(8): 2400-2406.
[15]	Li LIU, Haijin HOU, Anhong WANG, Tao ZHANG. Generative data hiding algorithm based on multi-scale attention [J]. Journal of Computer Applications, 2024, 44(7): 2102-2109.