Synthesizing Programs for Images using Reinforced Adversarial Learning

Yaroslav Ganin, Tejas Kulkarni, Igor Babuschkin, S. M. Ali Eslami, Oriol Vinyals
Proceedings of the 35th International Conference on Machine Learning, PMLR 80:1666-1675, 2018.

Abstract

Advances in deep generative networks have led to impressive results in recent years. Nevertheless, such models can often waste their capacity on the minutiae of datasets, presumably due to weak inductive biases in their decoders. This is where graphics engines may come in handy since they abstract away low-level details and represent images as high-level programs. Current methods that combine deep learning and renderers are limited by hand-crafted likelihood or distance functions, a need for large amounts of supervision, or difficulties in scaling their inference algorithms to richer datasets. To mitigate these issues, we present SPIRAL, an adversarially trained agent that generates a program which is executed by a graphics engine to interpret and sample images. The goal of this agent is to fool a discriminator network that distinguishes between real and rendered data, trained with a distributed reinforcement learning setup without any supervision. A surprising finding is that using the discriminator’s output as a reward signal is the key to allow the agent to make meaningful progress at matching the desired output rendering. To the best of our knowledge, this is the first demonstration of an end-to-end, unsupervised and adversarial inverse graphics agent on challenging real world (MNIST, Omniglot, CelebA) and synthetic 3D datasets. A video of the agent can be found at https://youtu.be/iSyvwAwa7vk.

Cite this Paper


BibTeX
@InProceedings{pmlr-v80-ganin18a, title = {Synthesizing Programs for Images using Reinforced Adversarial Learning}, author = {Ganin, Yaroslav and Kulkarni, Tejas and Babuschkin, Igor and Eslami, S. M. Ali and Vinyals, Oriol}, booktitle = {Proceedings of the 35th International Conference on Machine Learning}, pages = {1666--1675}, year = {2018}, editor = {Dy, Jennifer and Krause, Andreas}, volume = {80}, series = {Proceedings of Machine Learning Research}, month = {10--15 Jul}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v80/ganin18a/ganin18a.pdf}, url = {https://proceedings.mlr.press/v80/ganin18a.html}, abstract = {Advances in deep generative networks have led to impressive results in recent years. Nevertheless, such models can often waste their capacity on the minutiae of datasets, presumably due to weak inductive biases in their decoders. This is where graphics engines may come in handy since they abstract away low-level details and represent images as high-level programs. Current methods that combine deep learning and renderers are limited by hand-crafted likelihood or distance functions, a need for large amounts of supervision, or difficulties in scaling their inference algorithms to richer datasets. To mitigate these issues, we present SPIRAL, an adversarially trained agent that generates a program which is executed by a graphics engine to interpret and sample images. The goal of this agent is to fool a discriminator network that distinguishes between real and rendered data, trained with a distributed reinforcement learning setup without any supervision. A surprising finding is that using the discriminator’s output as a reward signal is the key to allow the agent to make meaningful progress at matching the desired output rendering. To the best of our knowledge, this is the first demonstration of an end-to-end, unsupervised and adversarial inverse graphics agent on challenging real world (MNIST, Omniglot, CelebA) and synthetic 3D datasets. A video of the agent can be found at https://youtu.be/iSyvwAwa7vk.} }
Endnote
%0 Conference Paper %T Synthesizing Programs for Images using Reinforced Adversarial Learning %A Yaroslav Ganin %A Tejas Kulkarni %A Igor Babuschkin %A S. M. Ali Eslami %A Oriol Vinyals %B Proceedings of the 35th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2018 %E Jennifer Dy %E Andreas Krause %F pmlr-v80-ganin18a %I PMLR %P 1666--1675 %U https://proceedings.mlr.press/v80/ganin18a.html %V 80 %X Advances in deep generative networks have led to impressive results in recent years. Nevertheless, such models can often waste their capacity on the minutiae of datasets, presumably due to weak inductive biases in their decoders. This is where graphics engines may come in handy since they abstract away low-level details and represent images as high-level programs. Current methods that combine deep learning and renderers are limited by hand-crafted likelihood or distance functions, a need for large amounts of supervision, or difficulties in scaling their inference algorithms to richer datasets. To mitigate these issues, we present SPIRAL, an adversarially trained agent that generates a program which is executed by a graphics engine to interpret and sample images. The goal of this agent is to fool a discriminator network that distinguishes between real and rendered data, trained with a distributed reinforcement learning setup without any supervision. A surprising finding is that using the discriminator’s output as a reward signal is the key to allow the agent to make meaningful progress at matching the desired output rendering. To the best of our knowledge, this is the first demonstration of an end-to-end, unsupervised and adversarial inverse graphics agent on challenging real world (MNIST, Omniglot, CelebA) and synthetic 3D datasets. A video of the agent can be found at https://youtu.be/iSyvwAwa7vk.
APA
Ganin, Y., Kulkarni, T., Babuschkin, I., Eslami, S.M.A. & Vinyals, O.. (2018). Synthesizing Programs for Images using Reinforced Adversarial Learning. Proceedings of the 35th International Conference on Machine Learning, in Proceedings of Machine Learning Research 80:1666-1675 Available from https://proceedings.mlr.press/v80/ganin18a.html.

Related Material