Multi-scale attention network for image super-resolution

Wang, Li; Shen, Jie; Tang, E.; Zheng, Shengnan; Xu, Lizhong

doi:10.1016/j.jvcir.2021.103300

Cited by 16 publications

(16 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…On the whole, MAFDN achieves the best performance on all fve datasets. Specifcally, compared with the recent proposed FDIWN [38], DDistill-SR [39], PILN [3], DRSAN [40], ESRT [67], FDSCSR [64], LESR [62], AFAN [61], and FRN [65], on the whole, our MAFDN obtains better performance with comparable or fewer parameters. For example, the proposed MAFDN achieves 0.15 dB/0.0005, 0.17 dB/0.0019, and 0.21 dB/0.0037 PSNR/ SSIM gains over the recent attention-based model AFAN [61] (682K/681K/692K) for × 2, × 3, and × 4 SR on Set5, respectively.…”

Section: Lightweight Sisr Methods For Comparisonsmentioning

confidence: 84%

“…To demonstrate the capacity and superiority of MAFDN, representative lightweight SISR methods and recent proposed state-of-the-art models are compared, i.e., SRCNN [19], PAN [74], RFDN [58], FDIWN [38], DDistill-SR [39], PILN [3], JSNet [70], DiVANet [59], EMASRN [60], DRSAN [40], ESRT [67], MMSR [68], HPUN [66], FDSCSR [64], LESR [62], IRN [63], AFAN [61], and FRN [65]. Overall, these competitors cover attention-based, feature distillationbased, and NAS-based SISR models.…”

Section: Lightweight Sisr Methods For Comparisonsmentioning

confidence: 99%

“…Wang et al [61] integrated channel attention and multi-aware attention modules to capture multiple content-aware information at lower model complexity. Tang et al [62] developed a lightweight SR using sparse self-attention and spatial/channel masks.…”

Section: Lightweight Cnn For Complexity-oriented Sisrmentioning

confidence: 99%

See 2 more Smart Citations

A Multi-Attention Feature Distillation Neural Network for Lightweight Single Image Super-Resolution

Zhang,

Lin,

Yang

et al. 2024

International Journal of Intelligent Systems

View full text Add to dashboard Cite

In recent years, remarkable performance improvements have been produced by deep convolutional neural networks (CNN) for single image super-resolution (SISR). Nevertheless, a high proportion of CNN-based SISR models are with quite a few network parameters and high computational complexity for deep or wide architectures. How to more fully utilize deep features to make a balance between model complexity and reconstruction performance is one of the main challenges in this field. To address this problem, on the basis of the well-known information multi-distillation model, a multi-attention feature distillation network termed as MAFDN is developed for lightweight and accurate SISR. Specifically, an effective multi-attention feature distillation block (MAFDB) is designed and used as the basic feature extraction unit in MAFDN. With the help of multi-attention layers including pixel attention, spatial attention, and channel attention, MAFDB uses multiple information distillation branches to learn more discriminative and representative features. Furthermore, MAFDB introduces the depthwise over-parameterized convolutional layer (DO-Conv)-based residual block (OPCRB) to enhance its ability without incurring any parameter and computation increase in the inference stage. The results on commonly used datasets demonstrate that our MAFDN outperforms existing representative lightweight SISR models when taking both reconstruction performance and model complexity into consideration. For example, for ×4 SR on Set5, MAFDN (597K/33.79G) obtains 0.21 dB/0.0037 and 0.10 dB/0.0015 PSNR/SSIM gains over the attention-based SR model AFAN (692K/50.90G) and the feature distillation-based SR model DDistill-SR (675K/32.83G), respectively.

show abstract

Section: Lightweight Sisr Methods For Comparisonsmentioning

confidence: 84%

Section: Lightweight Sisr Methods For Comparisonsmentioning

confidence: 99%

See 1 more Smart Citation

A Multi-Attention Feature Distillation Neural Network for Lightweight Single Image Super-Resolution

Zhang,

Lin,

Yang

et al. 2024

International Journal of Intelligent Systems

View full text Add to dashboard Cite

show abstract

“…Very recently, the attention mechanism has acquired wide applications in SR tasks. 29,31,32 Zhang et al 33 pioneered the introduction of channel attention (CA) to image SR reconstruction and showed prominent restoration results. Li 34 introduced a novel spatial attention (SA) that learned a group of weights to emphasize high-frequency information.…”

Section: Introductionmentioning

confidence: 99%

“…Very recently, the attention mechanism has acquired wide applications in SR tasks 29 , 31 , 32 . Zhang et al 33 .…”

Section: Introductionmentioning

confidence: 99%

Lightweight frequency-based attention network for image super-resolution

Tang

Wang

et al. 2022

J. Electron. Imag.

Self Cite

View full text Add to dashboard Cite

. The advent of convolutional neural networks has been driving the rapid development of image super-resolution (SR) tasks. Existing works, however, tend to devise deeper and wider networks to boost accuracy, leading to huge model sizes and computation costs. In addition, they also ignore the effect of frequency domain information on image restoration. To address these challenges, we propose a simple and effective frequency-based attention network, comprising a series of frequency-domain enhancement modules (FDEMs), for accurate image SR. Each FDEM integrates a two-dimensional discrete wavelet transform, progressive frequency enhancement module (PFEM), and frequency aggregation module (FAM). Specifically, DWT first decomposes the features into high-frequency and low-frequency parts, and then the low-frequency branch is processed and gradually added to the high-frequency branch to realize the interaction of frequency information in PFEM. Finally, frequency representations from the PFEM are upsampled to the FAM to further achieve information enhancement in a specific space. Extensive experiments indicate that our method is efficient in reconstruction accuracy with less model capacity, exceeding most existing lightweight SR networks.

show abstract