Re-GAN: Data-Efficient GANs Training via Architectural Reconfiguration
Divya Saxena, Jiannong Cao, Jiahao Xu, Tarun Kulshrestha
2023Year
2Top-tier citations
Abstract
Figure 1: Results of our proposed Re-GAN where dynamically GANs architecture is reconfigured to explore different GANs subnetwork structures during training time. (left) Image generation trained on multiple few-shot generation datasets, such as 100-shot Obama [1], Panda [1], and Animal Face-Cat (A-Cat) [2]; (right) FID scores vs. CIFAR-10 [3] training set size with training cost, FLOPs. Best viewed in color.
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Cited by top-tier papers2
- RG-GAN: Dynamic Regenerative Pruning for Data-Efficient Generative Adversarial NetworksDivya Saxena, Jiannong Cao, Jiahao Xu, Tarun KulshresthaAAAI 2024 · 11 citations
- Improving Few-shot Image Generation by Structural Discrimination and Textural ModulationMengping Yang, Zhe Wang, Wenyi Feng, Qian Zhang et al.ACM MM 2023 · 4 citations
Builds on21
- Training Generative Adversarial Networks with Limited DataTero Karras, Miika Aittala, Janne Hellsten, Samuli Laine et al.NeurIPS 2020 · 2,345 citations
- Linear Mode Connectivity and the Lottery Ticket HypothesisJonathan Frankle, Gintare Karolina Dziugaite, Daniel M. Roy, Michael CarbinICML 2020 · 750 citations
- Differentiable Augmentation for Data-Efficient GAN TrainingShengyu Zhao, Zhijian Liu, Ji Lin, Jun-Yan Zhu et al.NeurIPS 2020 · 707 citations
- Comparing Rewinding and Fine-tuning in Neural Network PruningAlex Renda, Jonathan Frankle, Michael CarbinICLR 2020 · 437 citations
- Towards Faster and Stabilized GAN Training for High-fidelity Few-shot Image SynthesisBingchen Liu, Yizhe Zhu, Kunpeng Song, Ahmed ElgammalICLR 2021 · 307 citations
Related papers
- AutoGAN: Neural Architecture Search for Generative Adversarial NetworksXinyu Gong, Shiyu Chang, Yifan Jiang, Zhangyang WangICCV 2019 · 286 citations
- Regularizing Generative Adversarial Networks Under Limited DataHung-Yu Tseng, Lu Jiang, Ce Liu, Ming-Hsuan Yang et al.CVPR 2021
- Sequential Training of GANs Against GAN-Classifiers Reveals Correlated "Knowledge Gaps" Present Among Independently Trained GAN InstancesArkanath Pathak, Nicholas DufourCVPR 2023
- Data-Efficient GAN Training Beyond (Just) Augmentations: A Lottery Ticket PerspectiveTianlong Chen, Yu Cheng, Zhe Gan, Jingjing Liu et al.NeurIPS 2021 · 61 citations
- Where is My Spot? Few-shot Image Generation via Latent Subspace OptimizationChenxi Zheng, Bangzhen Liu, Huaidong Zhang, Xuemiao Xu et al.CVPR 2023
