Swift Parameter-free Attention Network for Efficient Super-Resolution

• URL: http://arxiv.org/abs/2311.12770v3
• Date: Sun, 12 May 2024 04:29:54 GMT
• Title: Swift Parameter-free Attention Network for Efficient Super-Resolution
• Authors: Cheng Wan, Hongyuan Yu, Zhiqi Li, Yihang Chen, Yajun Zou, Yuqing Liu, Xuanwu Yin, Kunlong Zuo,
• Abstract summary: Single Image Super-Resolution is a crucial task in low-level computer vision. We propose the Swift. parameter-free Attention Network (SPAN), which balances parameter count, inference speed, and image quality. We evaluate SPAN on multiple benchmarks, showing that it outperforms existing efficient super-resolution models in terms of both image quality and inference speed.
• Score: 8.365929625909509
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Single Image Super-Resolution (SISR) is a crucial task in low-level computer vision, aiming to reconstruct high-resolution images from low-resolution counterparts. Conventional attention mechanisms have significantly improved SISR performance but often result in complex network structures and large number of parameters, leading to slow inference speed and large model size. To address this issue, we propose the Swift Parameter-free Attention Network (SPAN), a highly efficient SISR model that balances parameter count, inference speed, and image quality. SPAN employs a novel parameter-free attention mechanism, which leverages symmetric activation functions and residual connections to enhance high-contribution information and suppress redundant information. Our theoretical analysis demonstrates the effectiveness of this design in achieving the attention mechanism's purpose. We evaluate SPAN on multiple benchmarks, showing that it outperforms existing efficient super-resolution models in terms of both image quality and inference speed, achieving a significant quality-speed trade-off. This makes SPAN highly suitable for real-world applications, particularly in resource-constrained scenarios. Notably, we won the first place both in the overall performance track and runtime track of the NTIRE 2024 efficient super-resolution challenge. Our code and models are made publicly available at https://github.com/hongyuanyu/SPAN.

Related papers

• Large Kernel Distillation Network for Efficient Single Image Super-Resolution [8.094254341695684]
  Single-image super-resolution (SISR) has achieved remarkable performance in recent years. Current state-of-the-art (SOTA) models still face problems such as high computational costs. We propose the Large Kernel Distillation Network (LKDN) in this paper.
  arXiv  Detail & Related papers  (2024-07-19T14:21:56Z)
• Incorporating Transformer Designs into Convolutions for Lightweight Image Super-Resolution [46.32359056424278]
  Large convolutional kernels have become popular in designing convolutional neural networks. The increase in kernel size also leads to a quadratic growth in the number of parameters, resulting in heavy computation and memory requirements. We propose a neighborhood attention (NA) module that upgrades the standard convolution with a self-attention mechanism. Building upon the NA module, we propose a lightweight single image super-resolution (SISR) network named TCSR.
  arXiv  Detail & Related papers  (2023-03-25T01:32:18Z)
• RDRN: Recursively Defined Residual Network for Image Super-Resolution [58.64907136562178]
  Deep convolutional neural networks (CNNs) have obtained remarkable performance in single image super-resolution. We propose a novel network architecture which utilizes attention blocks efficiently.
  arXiv  Detail & Related papers  (2022-11-17T11:06:29Z)
• Efficient Image Super-Resolution using Vast-Receptive-Field Attention [49.87316814164699]
  The attention mechanism plays a pivotal role in designing advanced super-resolution (SR) networks. In this work, we design an efficient SR network by improving the attention mechanism. We propose VapSR, the VAst-receptive-field Pixel attention network.
  arXiv  Detail & Related papers  (2022-10-12T07:01:00Z)
• Fourier Space Losses for Efficient Perceptual Image Super-Resolution [131.50099891772598]
  We show that it is possible to improve the performance of a recently introduced efficient generator architecture solely with the application of our proposed loss functions. We show that our losses' direct emphasis on the frequencies in Fourier-space significantly boosts the perceptual image quality. The trained generator achieves comparable results with and is 2.4x and 48x faster than state-of-the-art perceptual SR methods RankSRGAN and SRFlow respectively.
  arXiv  Detail & Related papers  (2021-06-01T20:34:52Z)
• Asymmetric CNN for image super-resolution [102.96131810686231]
  Deep convolutional neural networks (CNNs) have been widely applied for low-level vision over the past five years. We propose an asymmetric CNN (ACNet) comprising an asymmetric block (AB), a mem?ory enhancement block (MEB) and a high-frequency feature enhancement block (HFFEB) for image super-resolution. Our ACNet can effectively address single image super-resolution (SISR), blind SISR and blind SISR of blind noise problems.
  arXiv  Detail & Related papers  (2021-03-25T07:10:46Z)
• Lightweight Image Super-Resolution with Multi-scale Feature Interaction Network [15.846394239848959]
  We present a lightweight multi-scale feature interaction network (MSFIN) For lightweight SISR, MSFIN expands the receptive field and adequately exploits the informative features of the low-resolution observed images. Our proposed MSFIN can achieve comparable performance against the state-of-the-arts with a more lightweight model.
  arXiv  Detail & Related papers  (2021-03-24T07:25:21Z)
• Fully Quantized Image Super-Resolution Networks [81.75002888152159]
  We propose a Fully Quantized image Super-Resolution framework (FQSR) to jointly optimize efficiency and accuracy. We apply our quantization scheme on multiple mainstream super-resolution architectures, including SRResNet, SRGAN and EDSR. Our FQSR using low bits quantization can achieve on par performance compared with the full-precision counterparts on five benchmark datasets.
  arXiv  Detail & Related papers  (2020-11-29T03:53:49Z)
• Journey Towards Tiny Perceptual Super-Resolution [23.30464519074935]
  We propose a neural architecture search (NAS) approach that integrates NAS and generative adversarial networks (GANs) with recent advances in perceptual SR. Our tiny perceptual SR (TPSR) models outperform SRGAN and EnhanceNet on both full-reference perceptual metric (LPIPS) and distortion metric (PSNR)
  arXiv  Detail & Related papers  (2020-07-08T18:24:40Z)
• Toward fast and accurate human pose estimation via soft-gated skip connections [97.06882200076096]
  This paper is on highly accurate and highly efficient human pose estimation. We re-analyze this design choice in the context of improving both the accuracy and the efficiency over the state-of-the-art. Our model achieves state-of-the-art results on the MPII and LSP datasets.
  arXiv  Detail & Related papers  (2020-02-25T18:51:51Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.