Flow Plugin Network for conditional generation
Not on the map. Why?
Abstract (arXiv)
Generative models have gained many researchers' attention in the last years resulting in models such as StyleGAN for human face generation or PointFlow for the 3D point cloud generation. However, by default, we cannot control its sampling process, i.e., we cannot generate a sample with a specific set of attributes. The current approach is model retraining with additional inputs and different architecture, which requires time and computational resources. We propose a novel approach that enables to a generation of objects with a given set of attributes without retraining the base model. For this purpose, we utilize the normalizing flow models - Conditional Masked Autoregressive Flow and Conditional Real NVP, as a Flow Plugin Network (FPN).
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 22 of its 28 references that are in the map. First posted on arXiv 7 Oct 2021.
Builds on
22 of 28 references.
References · 22
- 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 6,013
- 2014Deep Learning Face Attributes in the Wildcited by 3,693
- 2018UMAP: Uniform Manifold Approximation and Projection for Dimension Reductioncited by 2,898
- 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,897
- 2016Density estimation using Real NVPcited by 2,042
- 2019Normalizing Flows for Probabilistic Modeling and Inferencecited by 1,323
- 2017Masked Autoregressive Flow for Density Estimationcited by 684
- 2018FFJORD: Free-form Continuous Dynamics for Scalable Reversible Generative Modelscited by 594
- 2016Conditional Image Synthesis With Auxiliary Classifier GANscited by 565
- 2019PointFlow: 3D Point Cloud Generation with Continuous Normalizing Flowscited by 488
- 2015Adversarial Autoencoderscited by 364
- 2020StyleFlow: Attribute-conditioned Exploration of StyleGAN-Generated Images using Conditional Continuous Normalizing Flowscited by 349
10 more
- 2017Learning Discourse-level Diversity for Neural Dialog Models using Conditional Variational Autoencoderscited by 222
- 2020SRFlow: Learning the Super-Resolution Space with Normalizing Flowcited by 209
- 2019Noise Flow: Noise Modeling with Conditional Normalizing Flowscited by 108
- 2015Attribute2Image: Conditional Image Generation from Visual Attributescited by 93
- 2019C-Flow: Conditional Generative Flow Models for Images and 3D Point Cloudscited by 50
- 2019Conditional Flow Variational Autoencoders for Structured Sequence Predictioncited by 37
- 2019Semi-Conditional Normalizing Flows for Semi-Supervised Learningcited by 15
- 2019Latent Space Factorisation and Manipulation via Matrix Subspace Projectioncited by 9
- 2019Plugin Networks for Inference under Partial Evidencecited by 2
- 2021Guiding GANs: How to control non-conditional pre-trained GANs for conditional image generationcited by 1
Built on by
Citing papers per year: 2023: 1.
1 paper.