DatasetGAN: Efficient Labeled Data Factory With Minimal Human Effort
Yuxuan Zhang, Huan Ling, Jun Gao, Kangxue Yin, Jean-Francois Lafleche, Adela Barriuso, Antonio Torralba, Sanja Fidler
摘要
Train DatasetGAN Manual annotation of few generated images Sample from the DatasetGAN a large synthetic dataset Train on synthetic and test on Real Images 2 3 4 1 Figure 1: DATASETGAN synthesizes image-annotation pairs, and can produce large high-quality datasets with detailed pixel-wise labels. Figure illustrates the 4 steps. (1 & 2). Leverage StyleGAN and annotate only a handful of synthesized images. Train a highly effective branch to generate labels. (3). Generate a huge synthetic dataset of annotated images authomatically. (4). Train your favorite approach with the synthetic dataset and test on real images.
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了每一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。
引用它的顶会 Paper102
- Label-Efficient Semantic Segmentation with Diffusion ModelsDmitry Baranchuk, Andrey Voynov, Ivan Rubachev, Valentin Khrulkov 等ICLR 2022 · 被引用 700 次
- GET3D: A Generative Model of High Quality 3D Textured Shapes Learned from ImagesJun Gao, Tianchang Shen, Zian Wang, Wenzheng Chen 等NeurIPS 2022 · 被引用 661 次
- Emergent Correspondence from Image DiffusionLuming Tang, Menglin Jia, Qianqian Wang, Cheng Perng Phoo 等NeurIPS 2023 · 被引用 555 次
- Effective Data Augmentation With Diffusion ModelsBrandon Trabucco, Kyle Doherty, Max Gurinas, Ruslan SalakhutdinovICLR 2024 · 被引用 380 次
- Your Diffusion Model is Secretly a Zero-Shot ClassifierAlexander C. Li, Mihir Prabhudesai, Shivam Duggal, Ellis Brown 等ICCV 2023 · 被引用 341 次
它引用的顶会 Paper10
- A Simple Framework for Contrastive Learning of Visual RepresentationsTing Chen, Simon Kornblith, Mohammad Norouzi, Geoffrey E. HintonICML 2020 · 被引用 24,064 次
- Bootstrap Your Own Latent - A New Approach to Self-Supervised LearningJean-Bastien Grill, Florian Strub, Florent Altché, Corentin Tallec 等NeurIPS 2020 · 被引用 9,171 次
- FixMatch: Simplifying Semi-Supervised Learning with Consistency and ConfidenceKihyuk Sohn, David Berthelot, Nicholas Carlini, Zizhao Zhang 等NeurIPS 2020 · 被引用 5,129 次
- Big Self-Supervised Models are Strong Semi-Supervised LearnersTing Chen, Simon Kornblith, Kevin Swersky, Mohammad Norouzi 等NeurIPS 2020 · 被引用 2,611 次
- Invariant Information Clustering for Unsupervised Image Classification and SegmentationXu Ji, Andrea Vedaldi, João F. HenriquesICCV 2019 · 被引用 956 次
相关 Paper
- BigDatasetGAN: Synthesizing ImageNet with Pixel-wise AnnotationsDaiqing Li, Huan Ling, Seung Wook Kim, Karsten Kreis 等CVPR 2022 · 被引用 71 次
- Network-Free, Unsupervised Semantic Segmentation with Synthetic ImagesQianli Feng, Raghudeep Gadde, Wentong Liao, Eduard Ramon 等CVPR 2023
- Semantic Segmentation With Generative Models: Semi-Supervised Learning and Strong Out-of-Domain GeneralizationDaiqing Li, Junlin Yang, Karsten Kreis, Antonio Torralba 等CVPR 2021
- A Unified Generative Adversarial Network Training via Self-Labeling and Self-AttentionTomoki Watanabe, Paolo FavaroICML 2021 · 被引用 3 次
- StyleGAN-XL: Scaling StyleGAN to Large Diverse DatasetsAxel Sauer, Katja Schwarz, Andreas GeigerSIGGRAPH 2022 · 被引用 326 次
