PGGAN | Progressive Growing of GANs for Improved Quality, Stability, and Variation (part 2) | AISC

Published on ● Video Link: https://www.youtube.com/watch?v=fMds8t_Gt-I



Duration: 22:47
1,371 views
15


Toronto Deep Learning Series, 29 October 2018

Part 1: https://youtu.be/q7_TCtI2188

For slides and more information, visit: https://tdls.a-i.science/events/2018-10-22/

Paper: https://arxiv.org/abs/1710.10196

Speaker: Andrew Martin (Logojoy)

Host: Logojoy
Date: Oct 29th, 2018

Progressive Growing of GANs for Improved Quality, Stability, and Variation

We describe a new training methodology for generative adversarial networks. The key idea is to grow both the generator and discriminator progressively: starting from a low resolution, we add new layers that model increasingly fine details as training progresses. This both speeds the training up and greatly stabilizes it, allowing us to produce images of unprecedented quality, e.g., CelebA images at 1024^2. We also propose a simple way to increase the variation in generated images, and achieve a record inception score of 8.80 in unsupervised CIFAR10. Additionally, we describe several implementation details that are important for discouraging unhealthy competition between the generator and discriminator. Finally, we suggest a new metric for evaluating GAN results, both in terms of image quality and variation. As an additional contribution, we construct a higher-quality version of the CelebA dataset.




Other Videos By LLMs Explained - Aggregate Intellect - AI.SCIENCE


2018-12-05[DQN] Human-level control through deep reinforcement learning (discussions) | AISC Foundational
2018-12-05Deep Q-Learning paper explained: Human-level control through deep reinforcement learning (algorithm)
2018-12-03SMOTE, Synthetic Minority Over-sampling Technique (discussions) | AISC Foundational
2018-12-02TDLS - Classics: SMOTE, Synthetic Minority Over-sampling Technique (algorithm)
2018-11-30Visualizing Data using t-SNE (algorithm) | AISC Foundational
2018-11-30Visualizing Data using t-SNE (discussions) | AISC Foundational
2018-11-27[BERT] Pretranied Deep Bidirectional Transformers for Language Understanding (discussions) | TDLS
2018-11-27[BERT] Pretranied Deep Bidirectional Transformers for Language Understanding (algorithm) | TDLS
2018-11-27Neural Image Caption Generation with Visual Attention (algorithm) | AISC
2018-11-27Neural Image Caption Generation with Visual Attention (discussion) | AISC
2018-11-17PGGAN | Progressive Growing of GANs for Improved Quality, Stability, and Variation (part 2) | AISC
2018-11-16PGGAN | Progressive Growing of GANs for Improved Quality, Stability, and Variation (part 1) | AISC
2018-11-16(Original Paper) Latent Dirichlet Allocation (discussions) | AISC Foundational
2018-11-15(Original Paper) Latent Dirichlet Allocation (algorithm) | AISC Foundational
2018-10-31[Transformer] Attention Is All You Need | AISC Foundational
2018-10-25[Original attention] Neural Machine Translation by Jointly Learning to Align and Translate | AISC
2018-10-16[StackGAN++] Realistic Image Synthesis with Stacked Generative Adversarial Networks | AISC
2018-10-11Bayesian Deep Learning on a Quantum Computer | TDLS Author Speaking
2018-10-02Prediction of Cardiac arrest from physiological signals in the pediatric ICU | TDLS Author Speaking
2018-09-24Junction Tree Variational Autoencoder for Molecular Graph Generation | TDLS
2018-09-19Reconstructing quantum states with generative models | TDLS Author Speaking



Tags:
gans
machine vision
deep learning
machine learning
ai
artificial intelligence
generative adversarial networks
progressive growing gans
computer science
science
toronto
progressive gan