Timezone: »
Generative Adversarial Networks (GANs) can generate near photo realistic images in narrow domains such as human faces. Yet, modeling complex distributions of datasets such as ImageNet and COCO-Stuff remains challenging in unconditional settings. In this paper, we take inspiration from kernel density estimation techniques and introduce a non-parametric approach to modeling distributions of complex datasets. We partition the data manifold into a mixture of overlapping neighborhoods described by a datapoint and its nearest neighbors, and introduce a model, called instance-conditioned GAN (IC-GAN), which learns the distribution around each datapoint. Experimental results on ImageNet and COCO-Stuff show that IC-GAN significantly improves over unconditional models and unsupervised data partitioning baselines. Moreover, we show that IC-GAN can effortlessly transfer to datasets not seen during training by simply changing the conditioning instances, and still generate realistic images. Finally, we extend IC-GAN to the class-conditional case and show semantically controllable generation and competitive quantitative results on ImageNet; while improving over BigGAN on ImageNet-LT. Code and trained models to reproduce the reported results are available at https://github.com/facebookresearch/ic_gan.
Author Information
Arantxa Casanova (Polytechnique Montreal / Mila)
Marlene Careil (Facebook)
Jakob Verbeek (INRIA)
Michal Drozdzal (FAIR)
Adriana Romero Soriano (Facebook AI Research)
Related Events (a corresponding poster, oral, or spotlight)
-
2021 Poster: Instance-Conditioned GAN »
Thu. Dec 9th 04:30 -- 06:00 PM Room
More from the Same Authors
-
2021 : Benchmarking Bias Mitigation Algorithms in Representation Learning through Fairness Metrics »
Charan Reddy · Deepak Sharma · Soroush Mehri · Adriana Romero Soriano · Samira Shabanian · Sina Honari -
2021 Poster: XCiT: Cross-Covariance Image Transformers »
Alaaeldin Ali · Hugo Touvron · Mathilde Caron · Piotr Bojanowski · Matthijs Douze · Armand Joulin · Ivan Laptev · Natalia Neverova · Gabriel Synnaeve · Jakob Verbeek · Herve Jegou -
2021 Poster: Active 3D Shape Reconstruction from Vision and Touch »
Edward Smith · David Meger · Luis Pineda · Roberto Calandra · Jitendra Malik · Adriana Romero Soriano · Michal Drozdzal -
2021 Poster: Parameter Prediction for Unseen Deep Architectures »
Boris Knyazev · Michal Drozdzal · Graham Taylor · Adriana Romero Soriano -
2020 Poster: Instance Selection for GANs »
Terrance DeVries · Michal Drozdzal · Graham Taylor -
2020 Poster: 3D Shape Reconstruction from Vision and Touch »
Edward Smith · Roberto Calandra · Adriana Romero · Georgia Gkioxari · David Meger · Jitendra Malik · Michal Drozdzal -
2019 Workshop: Science meets Engineering of Deep Learning »
Levent Sagun · Caglar Gulcehre · Adriana Romero Soriano · Negar Rostamzadeh · Nando de Freitas -
2019 : Welcoming remarks and introduction »
Levent Sagun · Caglar Gulcehre · Adriana Romero Soriano · Negar Rostamzadeh · Nando de Freitas -
2019 Spotlight: Adaptive Density Estimation for Generative Models »
Thomas Lucas · Konstantin Shmelkov · Karteek Alahari · Cordelia Schmid · Jakob Verbeek -
2016 Poster: Convolutional Neural Fabrics »
Shreyas Saxena · Jakob Verbeek -
2010 Workshop: Beyond classification: Machine Learning for next generation Computer Vision challenges »
Craig Saunders · Jakob Verbeek · Svetlana Lazebnik -
2007 Oral: Scene Segmentation with CRFs Learned from Partially Labeled Images »
Jakob Verbeek · Bill Triggs -
2007 Poster: Scene Segmentation with CRFs Learned from Partially Labeled Images »
Jakob Verbeek · Bill Triggs