Open AccessPosted Content
Small-GAN: Speeding Up GAN Training Using Core-sets
Reads0
Chats0
TLDR
Experiments show that this technique substantially reduces training time and memory usage for modern GAN variants, that it reduces the fraction of dropped modes in a synthetic dataset, and that it allows GANs to reach a new state of the art in anomaly detection.Abstract:
Recent work by Brock et al. (2018) suggests that Generative Adversarial Networks (GANs) benefit disproportionately from large mini-batch sizes. Unfortunately, using large batches is slow and expensive on conventional hardware. Thus, it would be nice if we could generate batches that were effectively large though actually small. In this work, we propose a method to do this, inspired by the use of Coreset-selection in active learning. When training a GAN, we draw a large batch of samples from the prior and then compress that batch using Coreset-selection. To create effectively large batches of 'real' images, we create a cached dataset of Inception activations of each training image, randomly project them down to a smaller dimension, and then use Coreset-selection on those projected activations at training time. We conduct experiments showing that this technique substantially reduces training time and memory usage for modern GAN variants, that it reduces the fraction of dropped modes in a synthetic dataset, and that it allows GANs to reach a new state of the art in anomaly detection.read more
Citations
More filters
Posted Content
Freeze Discriminator: A Simple Baseline for Fine-tuning GANs.
Sangwoo Mo,Minsu Cho,Jinwoo Shin +2 more
TL;DR: It is shown that simple fine-tuning of GANs with frozen lower layers of the discriminator performs surprisingly well, and a simple baseline, FreezeD, significantly outperforms previous techniques used in both unconditional and conditional GAns.
Posted Content
Improved Consistency Regularization for GANs.
TL;DR: This work shows that consistency regularization can introduce artifacts into the GAN samples and proposes several modifications to the consistencyRegularization procedure designed to improve its performance, and yields the best known FID scores on various GAN architectures.
Proceedings ArticleDOI
CAFE: Learning to Condense Dataset by Aligning Features
Kai Wang,Bo Zhao,Zheng H. Zhu,Shuo Yang,Shuo Wang,Guan Huang,Hakan Bilen,Xinchao Wang,Yang You +8 more
TL;DR: This paper proposes a novel scheme to Condense dataset by Aligning FEatures (CAFE), which explicitly attempts to preserve the real-feature distribution as well as the discriminant power of the resulting synthetic set, lending itself to strong generalization capability to various architectures.
Proceedings ArticleDOI
DeepCore: A Comprehensive Library for Coreset Selection in Deep Learning
TL;DR: Extensive experiment results show that, although some methods perform better in certain experiment settings, random selection is still a strong baseline for coreset selection in deep learning.
Posted Content
Top-k Training of GANs: Improving GAN Performance by Throwing Away Bad Samples
TL;DR: A simple modification to the Generative Adversarial Network (GAN) training algorithm that materially improves results with no increase in computational cost is introduced: when updating the generator parameters, the gradient contributions from the elements of the batch that the critic scores as `least realistic' are zeroed out.
References
More filters
Proceedings Article
Attention is All you Need
Ashish Vaswani,Noam Shazeer,Niki Parmar,Jakob Uszkoreit,Llion Jones,Aidan N. Gomez,Lukasz Kaiser,Illia Polosukhin +7 more
TL;DR: This paper proposed a simple network architecture based solely on an attention mechanism, dispensing with recurrence and convolutions entirely and achieved state-of-the-art performance on English-to-French translation.
Journal ArticleDOI
Generative Adversarial Nets
Ian Goodfellow,Jean Pouget-Abadie,Mehdi Mirza,Bing Xu,David Warde-Farley,Sherjil Ozair,Aaron Courville,Yoshua Bengio +7 more
TL;DR: A new framework for estimating generative models via an adversarial process, in which two models are simultaneously train: a generative model G that captures the data distribution and a discriminative model D that estimates the probability that a sample came from the training data rather than G.
Dissertation
Learning Multiple Layers of Features from Tiny Images
TL;DR: In this paper, the authors describe how to train a multi-layer generative model of natural images, using a dataset of millions of tiny colour images, described in the next section.
Proceedings ArticleDOI
Image-to-Image Translation with Conditional Adversarial Networks
TL;DR: Conditional adversarial networks are investigated as a general-purpose solution to image-to-image translation problems and it is demonstrated that this approach is effective at synthesizing photos from label maps, reconstructing objects from edge maps, and colorizing images, among other tasks.
Proceedings ArticleDOI
Unpaired Image-to-Image Translation Using Cycle-Consistent Adversarial Networks
TL;DR: CycleGAN as discussed by the authors learns a mapping G : X → Y such that the distribution of images from G(X) is indistinguishable from the distribution Y using an adversarial loss.