Slimmable Generative Adversarial Networks
- URL: http://arxiv.org/abs/2012.05660v3
- Date: Thu, 18 Mar 2021 03:14:01 GMT
- Title: Slimmable Generative Adversarial Networks
- Authors: Liang Hou, Zehuan Yuan, Lei Huang, Huawei Shen, Xueqi Cheng, Changhu
Wang
- Abstract summary: Generative adversarial networks (GANs) have achieved remarkable progress in recent years, but the continuously growing scale of models makes them challenging to deploy widely in practical applications.
In this paper, we introduce slimmable GANs, which can flexibly switch the width of the generator to accommodate various quality-efficiency trade-offs at runtime.
- Score: 54.61774365777226
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Generative adversarial networks (GANs) have achieved remarkable progress in
recent years, but the continuously growing scale of models makes them
challenging to deploy widely in practical applications. In particular, for
real-time generation tasks, different devices require generators of different
sizes due to varying computing power. In this paper, we introduce slimmable
GANs (SlimGANs), which can flexibly switch the width of the generator to
accommodate various quality-efficiency trade-offs at runtime. Specifically, we
leverage multiple discriminators that share partial parameters to train the
slimmable generator. To facilitate the \textit{consistency} between generators
of different widths, we present a stepwise inplace distillation technique that
encourages narrow generators to learn from wide ones. As for class-conditional
generation, we propose a sliceable conditional batch normalization that
incorporates the label information into different widths. Our methods are
validated, both quantitatively and qualitatively, by extensive experiments and
a detailed ablation study.
Related papers
- A Block Metropolis-Hastings Sampler for Controllable Energy-based Text
Generation [78.81021361497311]
We develop a novel Metropolis-Hastings (MH) sampler that proposes re-writes of the entire sequence in each step via iterative prompting of a large language model.
Our new sampler allows for more efficient and accurate sampling from a target distribution and (b) allows generation length to be determined through the sampling procedure rather than fixed in advance.
arXiv Detail & Related papers (2023-12-07T18:30:15Z) - VOLTA: Improving Generative Diversity by Variational Mutual Information Maximizing Autoencoder [38.35049378875308]
We introduce VOLTA, a framework that elevates generative diversity by bridging Transformer with VAE.
We perform comprehensive experiments with two types of Transformers on six datasets to show that our approach can significantly improve generative diversity while maintaining generative quality.
arXiv Detail & Related papers (2023-07-03T08:45:42Z) - Start Small: Training Game Level Generators from Nothing by Learning at
Multiple Sizes [0.0]
A procedural level generator is a tool that generates levels from noise.
One approach to build generators is using machine learning, but given the training data rarity, multiple methods have been proposed to train generators from nothing.
This paper proposes a novel approach to train generators from nothing by learning at multiple level sizes starting from a small size up to the desired sizes.
arXiv Detail & Related papers (2022-09-29T18:52:54Z) - Twist Decoding: Diverse Generators Guide Each Other [116.20780037268801]
We introduce Twist decoding, a simple and general inference algorithm that generates text while benefiting from diverse models.
Our method does not assume the vocabulary, tokenization or even generation order is shared.
arXiv Detail & Related papers (2022-05-19T01:27:53Z) - Generative Cooperative Networks for Natural Language Generation [25.090455367573988]
We introduce Generative Cooperative Networks, in which the discriminator architecture is cooperatively used along with the generation policy to output samples of realistic texts.
We give theoretical guarantees of convergence for our approach, and study various efficient decoding schemes to empirically achieve state-of-the-art results in two main NLG tasks.
arXiv Detail & Related papers (2022-01-28T18:36:57Z) - Conditional Generative Modeling via Learning the Latent Space [54.620761775441046]
We propose a novel framework for conditional generation in multimodal spaces.
It uses latent variables to model generalizable learning patterns.
At inference, the latent variables are optimized to find optimal solutions corresponding to multiple output modes.
arXiv Detail & Related papers (2020-10-07T03:11:34Z) - GeDi: Generative Discriminator Guided Sequence Generation [53.15651536569169]
We propose GeDi as an efficient method for using smaller LMs as generative discriminators to guide generation from large LMs.
We find that GeDi gives stronger controllability than the state of the art method while also achieving generation speeds more than 30 times faster.
arXiv Detail & Related papers (2020-09-14T17:45:36Z) - Unsupervised Controllable Generation with Self-Training [90.04287577605723]
controllable generation with GANs remains a challenging research problem.
We propose an unsupervised framework to learn a distribution of latent codes that control the generator through self-training.
Our framework exhibits better disentanglement compared to other variants such as the variational autoencoder.
arXiv Detail & Related papers (2020-07-17T21:50:35Z) - Improving GANs for Speech Enhancement [19.836041050328102]
We propose to use multiple generators chained to perform multi-stage enhancement mapping.
We demonstrate that the proposed multi-stage enhancement approach outperforms the one-stage SEGAN baseline.
arXiv Detail & Related papers (2020-01-15T19:57:03Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.