mlsanityData to 7 Oct 2026

RingCNN: Exploiting Algebraically-Sparse Ring Tensors for Energy-Efficient CNN-Based Computational Imaging

arXiv 2104.09056 ↗First posted 19 Apr 2021cs.NE cs.LGcited by 3

Not on the map. Why?

Abstract (arXiv)

In the era of artificial intelligence, convolutional neural networks (CNNs) are emerging as a powerful technique for computational imaging. They have shown superior quality for reconstructing fine textures from badly-distorted images and have potential to bring next-generation cameras and displays to our daily life. However, CNNs demand intensive computing power for generating high-resolution videos and defy conventional sparsity techniques when rendering dense details. Therefore, finding new possibilities in regular sparsity is crucial to enable large-scale deployment of CNN-based computational imaging. In this paper, we consider a fundamental but yet well-explored approach -- algebraic sparsity -- for energy-efficient CNN acceleration. We propose to build CNN models based on ring algebra that defines multiplication, addition, and non-linearity for n-tuples properly. Then the essential sparsity will immediately follow, e.g. n-times reduction for the number of real-valued weights. We define and unify several variants of ring algebras into a modeling framework, RingCNN, and make comparisons in terms of image quality and hardware complexity. On top of that, we further devise a novel ring algebra which minimizes complexity with component-wise product and achieves the best quality using directional ReLU. Finally, we implement an accelerator, eRingCNN, in two settings, n=2 and 4 (50% and 75% sparsity), with 40 nm technology to support advanced denoising and super-resolution at up to 4K UHD 30 fps. Layout results show that they can deliver equivalent 41 TOPS using 3.76 W and 2.22 W, respectively. Compared to the real-valued counterpart, our ring convolution engines for n=2 achieve 2.00x energy efficiency and 2.08x area efficiency with similar or even better image quality. With n=4, the efficiency gains of energy and area are further increased to 3.84x and 3.77x with 0.11 dB drop of PSNR.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 30 of its 58 references that are in the map. First posted on arXiv 19 Apr 2021.

Builds on

30 of 58 references.

References · 30

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  3. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,773
  4. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,827
  5. 2016Perceptual Losses for Real-Time Style Transfer and Super-Resolutioncited by 2,678
  6. 2015Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Codingcited by 2,291
  7. 2016Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Networkcited by 1,898
  8. 2017Enhanced Deep Residual Networks for Single Image Super-Resolutioncited by 1,543
  9. 2016Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoisingcited by 1,352
  10. 2017ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devicescited by 1,194
  11. 2016SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model sizecited by 1,054
  12. 2015Accurate Image Super-Resolution Using Very Deep Convolutional Networkscited by 902
18 more
  1. 2017Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networkscited by 707
  2. 2017In-Datacenter Performance Analysis of a Tensor Processing Unitcited by 610
  3. 2018Object Detection with Deep Learning: A Reviewcited by 524
  4. 2017FFDNet: Toward a Fast and Flexible Solution for CNN based Image Denoisingcited by 509
  5. 2020Comparing Rewinding and Fine-tuning in Neural Network Pruningcited by 238
  6. 2017Deep Complex Networkscited by 215
  7. 2014Speeding-up Convolutional Neural Networks Using Fine-tuned CP-Decompositioncited by 199
  8. 2015Compression of Deep Convolutional Neural Networks for Fast and Low Power Mobile Applicationscited by 161
  9. 2017SCNN: An Accelerator for Compressed-sparse Convolutional Neural Networkscited by 132
  10. 2019Towards Efficient Model Compression via Learned Global Rankingcited by 75
  11. 2017CirCNN: Accelerating and Compressing Deep Neural Networks Using Block-CirculantWeight Matricescited by 53
  12. 2017Deep Quaternion Networkscited by 48
  13. 2019Quaternion Convolutional Neural Networkscited by 48
  14. 2017Exploring the Regularity of Sparse Structure in Convolutional Neural Networkscited by 37
  15. 2018Quaternion Convolutional Neural Networks for Heterogeneous Image Processingcited by 29
  16. 2020SmartExchange: Trading Higher-cost Memory Storage/Access for Lower-cost Computationcited by 16
  17. 2018Building Efficient Deep Neural Networks with Unitary Group Convolutionscited by 9
  18. 2019eCNN: A Block-Based and Highly-Parallel CNN Accelerator for Edge Inferencecited by 5

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 2.

3 papers.

  1. 2023SGCN: Exploiting Compressed-Sparse Features in Deep Graph Convolutional Network Acceleratorscited by 4
  2. 2023Slice-and-Forge: Making Better Use of Caches for Graph Convolutional Network Acceleratorscited by 1
  3. 2022DNNShield: Dynamic Randomized Model Sparsification, A Defense Against Adversarial Machine Learningcited by 0