mlsanityData to 14 Oct 2026

A Survey on GAN Acceleration Using Memory Compression Technique

arXiv 2108.06626 ↗First posted 14 Aug 2021cs.LG cs.CV cs.NEcited by 0

Not on the map. Why?

Abstract (arXiv)

Since its invention, Generative adversarial networks (GANs) have shown outstanding results in many applications. Generative Adversarial Networks are powerful yet, resource-hungry deep-learning models. Their main difference from ordinary deep learning models is the nature of their output. For example, GAN output can be a whole image versus other models detecting objects or classifying images. Thus, the architecture and numeric precision of the network affect the quality and speed of the solution. Hence, accelerating GANs is pivotal. Accelerating GANs can be classified into three main tracks: (1) Memory compression, (2) Computation optimization, and (3) Data-flow optimization. Because data transfer is the main source of energy usage, memory compression leads to the most savings. Thus, in this paper, we survey memory compression techniques for CNN-Based GANs. Additionally, the paper summarizes opportunities and challenges in GANs acceleration and suggests open research problems to be further investigated.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 35 of its 59 references that are in the map. First posted on arXiv 14 Aug 2021.

Builds on

35 of 59 references.

References · 35

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  2. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,527
  3. 2016Improved Techniques for Training GANscited by 2,970
  4. 2017Improved Training of Wasserstein GANscited by 2,235
  5. 2018DARTS: Differentiable Architecture Searchcited by 1,798
  6. 2020Knowledge Distillation: A Surveycited by 1,603
  7. 2017Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inferencecited by 1,593
  8. 2018ESRGAN: Enhanced Super-Resolution Generative Adversarial Networkscited by 1,254
  9. 2017High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANscited by 1,179
  10. 2017StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translationcited by 1,039
  11. 2016Least Squares Generative Adversarial Networkscited by 1,001
  12. 2019Once-for-All: Train One Network and Specialize it for Efficient Deploymentcited by 787
23 more
  1. 2017Learning Efficient Convolutional Networks through Network Slimmingcited by 676
  2. 2016StackGAN: Text to Photo-realistic Image Synthesis with Stacked Generative Adversarial Networkscited by 577
  3. 2020Knowledge Distillation and Student-Teacher Learning for Visual Intelligence: A Review and New Outlookscited by 316
  4. 2017A Survey of Model Compression and Acceleration for Deep Neural Networkscited by 301
  5. 2014Speeding up Convolutional Neural Networks with Low Rank Expansionscited by 284
  6. 2015Compressing Neural Networks with the Hashing Trickcited by 150
  7. 2019GANSynth: Adversarial Neural Audio Synthesiscited by 116
  8. 2017Soft Weight-Sharing for Neural Network Compressioncited by 99
  9. 2018Photographic Text-to-Image Synthesis with a Hierarchically-nested Adversarial Networkcited by 64
  10. 2020AutoGAN-Distiller: Searching to Compress Generative Adversarial Networkscited by 50
  11. 2017Flexpoint: An Adaptive Numerical Format for Efficient Training of Deep Neural Networkscited by 44
  12. 2020GAN Slimming: All-in-One GAN Compression by A Unified Optimization Frameworkcited by 44
  13. 2020Distilling portable Generative Adversarial Networks for Image Translationcited by 37
  14. 2021Teachers Do More Than Teach: Compressing Image-to-Image Modelscited by 37
  15. 2019Adversarial Video Generation on Complex Datasetscited by 33
  16. 2019Co-Evolutionary Compression for Unpaired Image Translationcited by 32
  17. 2019Compressing GANs using Knowledge Distillationcited by 31
  18. 2021Content-Aware GAN Compressioncited by 28
  19. 2019QGAN: Quantized Generative Adversarial Networkscited by 20
  20. 2020P-KDGAN: Progressive Knowledge Distillation with GANs for One-class Novelty Detectioncited by 11
  21. 2019Structured Multi-Hashing for Model Compressioncited by 10
  22. 2019Generative adversarial network-based glottal waveform model for statistical parametric speech synthesiscited by 7
  23. 2020Self-Supervised GAN Compressioncited by 6

Built on by

Not cited yet.