mlsanityData to 14 Oct 2026

Parameter-Free Channel Attention for Image Classification and Super-Resolution

arXiv 2303.11055 ↗First posted 20 Mar 2023eess.IV cs.CVcited by 3

Not on the map. Why?

Abstract (arXiv)

The channel attention mechanism is a useful technique widely employed in deep convolutional neural networks to boost the performance for image processing tasks, eg, image classification and image super-resolution. It is usually designed as a parameterized sub-network and embedded into the convolutional layers of the network to learn more powerful feature representations. However, current channel attention induces more parameters and therefore leads to higher computational costs. To deal with this issue, in this work, we propose a Parameter-Free Channel Attention (PFCA) module to boost the performance of popular image classification and image super-resolution networks, but completely sweep out the parameter growth of channel attention. Experiments on CIFAR-100, ImageNet, and DIV2K validate that our PFCA module improves the performance of ResNet on image classification and improves the performance of MSRResNet on image super-resolution tasks, respectively, while bringing little growth of parameters and FLOPs.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 25 of its 36 references that are in the map. First posted on arXiv 20 Mar 2023.

Builds on

25 of 36 references.

References · 25

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  4. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 7,005
  5. 2017Squeeze-and-Excitation Networkscited by 4,789
  6. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,548
  7. 2014Going Deeper with Convolutionscited by 4,241
  8. 2018CBAM: Convolutional Block Attention Modulecited by 2,477
  9. 2016Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Networkcited by 1,908
  10. 2017Enhanced Deep Residual Networks for Single Image Super-Resolutioncited by 1,552
  11. 2018Image Super-Resolution Using Very Deep Residual Channel Attention Networkscited by 1,264
  12. 2014Image Super-Resolution Using Deep Convolutional Networkscited by 1,224
13 more
  1. 2016Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Networkcited by 1,204
  2. 2015Accurate Image Super-Resolution Using Very Deep Convolutional Networkscited by 903
  3. 2019Selective Kernel Networkscited by 403
  4. 2015Sketch-based Manga Retrieval using Manga109 Datasetcited by 329
  5. 2018Fast, Accurate, and Lightweight Super-Resolution with Cascading Residual Networkcited by 264
  6. 2018BAM: Bottleneck Attention Modulecited by 172
  7. 2020Efficient Image Super-Resolution Using Pixel Attentioncited by 87
  8. 2021SA-Net: Shuffle Attention for Deep Convolutional Neural Networkscited by 54
  9. 2021Temporal Modulation Network for Controllable Space-Time Video Super-Resolutioncited by 54
  10. 2019Modulating Image Restoration with Continual Levels via Adaptive Feature Modification Layerscited by 39
  11. 2020AIM 2020 Challenge on Efficient Super-Resolution: Methods and Resultscited by 36
  12. 2018Parameter-Free Spatial Attention Network for Person Re-Identificationcited by 12
  13. 2018Sparse, Collaborative, or Nonnegative Representation: Which Helps Pattern Classification?cited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 1; 2024: 0; 2025: 0; 2026: 2.

3 papers.

  1. 2023Swift Parameter-free Attention Network for Efficient Super-Resolutioncited by 24
  2. 2026SwiftChannel: Algorithm-Hardware Co-Design for Deep Learning-Based 5G Channel Estimationcited by 1
  3. 2026Optimising CSRNet with parameter-free attention mechanisms for crowd counting in public transportcited by 0