CycleGANAS: Differentiable Neural Architecture Search for CycleGAN
Not on the map. Why?
Abstract (arXiv)
We develop a Neural Architecture Search (NAS) framework for CycleGAN that carries out unpaired image-to-image translation task. Extending previous NAS techniques for Generative Adversarial Networks (GANs) to CycleGAN is not straightforward due to the task difference and greater search space. We design architectures that consist of a stack of simple ResNet-based cells and develop a search method that effectively explore the large search space. We show that our framework, called CycleGANAS, not only effectively discovers high-performance architectures that either match or surpass the performance of the original CycleGAN, but also successfully address the data imbalance by individual architecture search for each translation direction. To our best knowledge, it is the first NAS result for CycleGAN and shed light on NAS for more complex structures.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 30 of its 43 references that are in the map. First posted on arXiv 13 Nov 2023.
Builds on
30 of 43 references.
References · 30
- 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,510
- 2018DARTS: Differentiable Architecture Searchcited by 1,782
- 2016Neural Architecture Search with Reinforcement Learningcited by 1,489
- 2018ESRGAN: Enhanced Super-Resolution Generative Adversarial Networkscited by 1,250
- 2018Efficient Neural Architecture Search via Parameter Sharingcited by 831
- 2018Which Training Methods for GANs do actually Converge?cited by 672
- 2018Generative Image Inpainting with Contextual Attentioncited by 578
- 2019AutoML: A Survey of the State-of-the-Artcited by 388
- 2016SeqGAN: Sequence Generative Adversarial Nets with Policy Gradientcited by 375
- 2017Toward Multimodal Image-to-Image Translationcited by 295
- 2017Learning to Discover Cross-Domain Relations with Generative Adversarial Networkscited by 278
- 2016Designing Neural Network Architectures using Reinforcement Learningcited by 277
18 more
- 2018Neural Architecture Search with Bayesian Optimisation and Optimal Transportcited by 192
- 2019MirrorGAN: Learning Text-to-image Generation by Redescriptioncited by 176
- 2019BANANAS: Bayesian Optimization with Neural Architectures for Neural Architecture Searchcited by 175
- 2017The Numerics of GANscited by 104
- 2018Translating and Segmenting Multimodal Medical Volumes with Cycle- and Shape-Consistency Generative Adversarial Networkcited by 97
- 2019AutoGAN: Neural Architecture Search for Generative Adversarial Networkscited by 94
- 2019Learning Graph Convolutional Network for Skeleton-based Human Action Recognition by Neural Searchingcited by 70
- 2019BayesNAS: A Bayesian Approach for Neural Architecture Searchcited by 67
- 2019CycleGAN-VC2: Improved CycleGAN-based Non-parallel Voice Conversioncited by 45
- 2020Geometry-Aware Gradient Algorithms for Neural Architecture Searchcited by 40
- 2019AdversarialNAS: Adversarial Neural Architecture Search for GANscited by 38
- 2019Co-Evolutionary Compression for Unpaired Image Translationcited by 32
- 2020Off-Policy Reinforcement Learning for Efficient and Effective GAN Architecture Searchcited by 25
- 2021OPANAS: One-Shot Path Aggregation Network Architecture Search for Object Detectioncited by 19
- 2018Evolving Space-Time Neural Architectures for Videoscited by 17
- 2019Asymmetric GAN for Unpaired Image-to-image Translationcited by 14
- 2022NAR-Former: Neural Architecture Representation Learning towards Holistic Attributes Predictioncited by 12
- 2019AGAN: Towards Automated Design of Generative Adversarial Networkscited by 8
Built on by
Citing papers per year: 2024: 1.
1 paper.