Inclusive GAN: Improving Data and Minority Coverage in Generative Models
By Ning Yu, Ke Li, Peng Zhou, Jitendra Malik, Larry S. Davis, Mario Fritz. 2020
69 citations recorded by the source corpus.
Generative Adversarial Networks (GANs) have brought about rapid progress towards generating photorealistic images. Yet the equitable allocation of their modeling capacity among subgroups has received less attention, which could lead to potential biases against underrepresented minorities if left uncontrolled. In this work, we first formalize the problem of minority inclusion as one of data coverage, and then propose to improve data coverage by harmonizing adversarial training with reconstructive generation. The experiments show that our method outperforms the existing state-of-the-art methods in terms of data coverage on both seen and unseen data. We develop an extension that allows explicit control over the minority subgroups that the model should ensure to include, and validate its effectiveness at little compromise from the overall performance on the entire dataset. Code, models, and supplemental videos are available at GitHub.
Subfields: Computer Vision and Pattern Recognition, Generative Models
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computer Vision and Pattern Recognition
- Luc Van Gool
- Ming-Hsuan Yang
- Dacheng Tao
- Trevor Darrell
- Xiaogang Wang
- Bernt Schiele
- Jitendra Malik
- Li Fei-Fei
In Generative Models
- Arash Vahdat
- Karsten Kreis
- Jan Kautz
- Zhisheng Xiao
- Andrew Tao
- Bryan Catanzaro
- Guilin Liu
- Larry S. Davis
Citations in the corpus
- VAEBM: A Symbiosis between Variational Autoencoders and Energy-based Models (2020, methodology): “Besides fundamental maximum likelihood training, other techniques to train EBMs exist, such as minimizing F-divergence (Yu et al., 2020a) or Stein discrepancy (Grathwohl et al., 2020b), contrastive estimation (Gutmann & Hyvärinen, 2010; Gao et al., 2020) and denoising score matching (Li et al.,…”
- Pros and Cons of GAN Evaluation Measures: New Developments (2021, background): “Some recent works ( e.g. Xu et al. (2018); Yu et al. (2020) have tried to mitigate the bias in GANs or use GANs to reduce bias in other ML algorithms ( e.g. Sattigeri et al. (2019); McDuff et al. (2019)).”
- Dual Contrastive Loss and Attention for GANs (2021, background): “Significant improvements are obtained by careful architectural designs for generators [10, 98, 42, 43, 69], discriminators [82, 56] and new regularization techniques [58, 3, 25, 60, 101, 105, 96, 40, 106, 36].”