mlsanityData to 7 Oct 2026

Coarse-to-Fine Searching for Efficient Generative Adversarial Networks

arXiv 2104.09223 ↗First posted 19 Apr 2021cs.CVcited by 3

Not on the map. Why?

Abstract (arXiv)

This paper studies the neural architecture search (NAS) problem for developing efficient generator networks. Compared with deep models for visual recognition tasks, generative adversarial network (GAN) are usually designed to conduct various complex image generation. We first discover an intact search space of generator networks including three dimensionalities, i.e., path, operator, channel for fully excavating the network performance. To reduce the huge search cost, we explore a coarse-to-fine search strategy which divides the overall search process into three sub-optimization problems accordingly. In addition, a fair supernet training approach is utilized to ensure that all sub-networks can be updated fairly and stably. Experiments results on benchmarks show that we can provide generator networks with better image quality and lower computational costs over the state-of-the-art methods. For example, with our method, it takes only about 8 GPU hours on the entire edges-to-shoes dataset to get a 2.56 MB model with a 24.13 FID score and 10 GPU hours on the entire Urban100 dataset to get a 1.49 MB model with a 24.94 PSNR score.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 62 of its 85 references that are in the map. First posted on arXiv 19 Apr 2021.

Builds on

62 of 85 references.

References · 62

  1. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  2. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,510
  3. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
  4. 2016Perceptual Losses for Real-Time Style Transfer and Super-Resolutioncited by 2,678
  5. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,609
  6. 2015Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Codingcited by 2,291
  7. 2017Improved Training of Wasserstein GANscited by 2,223
  8. 2014Conditional Generative Adversarial Netscited by 2,152
  9. 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,048
  10. 2016Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Networkcited by 1,898
  11. 2018DARTS: Differentiable Architecture Searchcited by 1,782
  12. 2014FitNets: Hints for Thin Deep Netscited by 1,619
38 more
  1. 2018Spectral Normalization for Generative Adversarial Networkscited by 1,618
  2. 2016Neural Architecture Search with Reinforcement Learningcited by 1,489
  3. 2019Semantic Image Synthesis with Spatially-Adaptive Normalizationcited by 1,295
  4. 2018ESRGAN: Enhanced Super-Resolution Generative Adversarial Networkscited by 1,250
  5. 2017High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANscited by 1,176
  6. 2017Learning Transferable Architectures for Scalable Image Recognitioncited by 1,097
  7. 2017StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translationcited by 1,036
  8. 2018MnasNet: Platform-Aware Neural Architecture Search for Mobilecited by 937
  9. 2015Accurate Image Super-Resolution Using Very Deep Convolutional Networkscited by 902
  10. 2018Regularized Evolution for Image Classifier Architecture Searchcited by 902
  11. 2018Multimodal Unsupervised Image-to-Image Translationcited by 795
  12. 2019Once-for-All: Train One Network and Specialize it for Efficient Deploymentcited by 778
  13. 2016Generative Adversarial Text to Image Synthesiscited by 735
  14. 2017Channel Pruning for Accelerating Very Deep Neural Networkscited by 697
  15. 2017Learning Efficient Convolutional Networks through Network Slimmingcited by 673
  16. 2018ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardwarecited by 666
  17. 2017Unsupervised Image-to-Image Translation Networkscited by 602
  18. 2016StackGAN: Text to Photo-realistic Image Synthesis with Stacked Generative Adversarial Networkscited by 575
  19. 2018FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Searchcited by 480
  20. 2019EnlightenGAN: Deep Light Enhancement without Paired Supervisioncited by 466
  21. 2018HAQ: Hardware-Aware Automated Quantization with Mixed Precisioncited by 426
  22. 2019Single Path One-Shot Neural Architecture Search with Uniform Samplingcited by 411
  23. 2018AMC: AutoML for Model Compression and Acceleration on Mobile Devicescited by 375
  24. 2017DualGAN: Unsupervised Dual Learning for Image-to-Image Translationcited by 310
  25. 2018Diverse Image-to-Image Translation via Disentangled Representationscited by 296
  26. 2016Learning from Simulated and Unsupervised Images through Adversarial Trainingcited by 287
  27. 2017Learning to Discover Cross-Domain Relations with Generative Adversarial Networkscited by 278
  28. 2019Progressive Differentiable Architecture Search: Bridging the Depth Gap between Search and Evaluationcited by 230
  29. 2015Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networkscited by 214
  30. 2020A Review on Generative Adversarial Networks: Algorithms, Theory, and Applicationscited by 209
  31. 2016EnhanceNet: Single Image Super-Resolution Through Automated Texture Synthesiscited by 177
  32. 2018Discrimination-aware Channel Pruning for Deep Neural Networkscited by 171
  33. 2017Fast and Accurate Image Super-Resolution with Deep Laplacian Pyramid Networkscited by 138
  34. 2018Unsupervised Image Super-Resolution using Cycle-in-Cycle Generative Adversarial Networkscited by 133
  35. 2019FairNAS: Rethinking Evaluation Fairness of Weight Sharing Neural Architecture Searchcited by 129
  36. 2019Fair DARTS: Eliminating Unfair Advantages in Differentiable Architecture Searchcited by 129
  37. 2016Unsupervised Cross-Domain Image Generationcited by 125
  38. 2020APQ: Joint Search for Network Architecture, Pruning and Quantization Policycited by 98

50 most cited of 62 All 62 (JSON)

Built on by

Cited by year

Citing papers per year: 2021: 2; 2022: 0; 2023: 1.

3 papers.

  1. 2021Revisiting Discriminator in GAN Compression: A Generator-discriminator Cooperative Compression Schemecited by 23
  2. 2023Compressing Image-to-Image Translation GANs Using Local Density Structures on Their Learned Manifoldcited by 3
  3. 2021DGL-GAN: Discriminator Guided Learning for GAN Compressioncited by 0