Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
By Alec Radford, Luke Metz, Soumith Chintala. 2015
15,179 citations recorded by the source corpus.
In recent years, supervised learning with convolutional networks (CNNs) has seen huge adoption in computer vision applications. Comparatively, unsupervised learning with CNNs has received less attention. In this work we hope to help bridge the gap between the success of CNNs for supervised learning and unsupervised learning. We introduce a class of CNNs called deep convolutional generative adversarial networks (DCGANs), that have certain architectural constraints, and demonstrate that they are a strong candidate for unsupervised learning. Training on various image datasets, we show convincing evidence that our deep convolutional adversarial pair learns a hierarchy of representations from object parts to scenes in both the generator and discriminator. Additionally, we use the learned features for novel tasks - demonstrating their applicability as general image representations.
Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Generative Models
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Yoshua Bengio
- Mohit Bansal
- Sergey Levine
- Quoc V. Le
- Jianfeng Gao
- Percy Liang
- Dacheng Tao
- Trevor Darrell
In Computer Vision and Pattern Recognition
- Luc Van Gool
- Dacheng Tao
- Ming-Hsuan Yang
- Trevor Darrell
- Xiaogang Wang
- Jitendra Malik
- Yi Yang
- Bernt Schiele
In Generative Models
- Stefano Ermon
- Jun-Yan Zhu
- Richard Zhang
- Yoshua Bengio
- Eli Shechtman
- Jiaming Song
- Arash Vahdat
- Alexei A. Efros
Citations in the corpus
- InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets (2016, methodology): “Since GAN is known to be difficult to train, we design our experiments based on existing techniques introduced by DC-GAN [16], which are enough to stabilize InfoGAN training and we did not have to introduce new trick.”
- Mixed Precision Training (2017, methodology): “The network was trained to generate 128x128 pixel images of faces, using DCGAN methodology (Radford et al., 2015) and CelebFaces dataset (Liu et al., 2015b).”
- Measuring Mathematical Problem Solving With the MATH Dataset (2021, methodology): “Because MATH answers must be generated, we use autoregressive language models, namely GPT-2 (Radford et al., 2016) and GPT-3 (Brown et al.”
- A Large-scale Study of Representation Learning with the Visual Task Adaptation Benchmark (2019, background): “Sometimes generative models are also evaluated using linear classification (Radford et al., 2016; Donahue et al., 2017; Dumoulin et al., 2017), or semi-supervised learning (Kingma et al., 2014; Narayanaswamy et al., 2017; Tschannen et al., 2018).”
- Image Transformer (2018, background): “They are notoriously unstable (Radford et al., 2015), motivating a large number of methods attempting to make their training more robust (Metz et al., 2016; Berthelot et al., 2017).”
- Are GANs Created Equal? A Large-Scale Study (2017, methodology): “Furthermore, it is similar to a proven architecture used in DCGAN [22].”
- Unsupervised Representation Learning by Predicting Image Rotations (2018, methodology): “…(Dosovitskiy et al., 2014; Liao et al., 2016; Yang et al., 2016), reconstruction based methods (Bengio et al., 2007; Huang et al., 2007; Masci et al., 2011), and methods that involve learning generative probabilistic models Goodfellow et al. (2014); Donahue et al. (2016); Radford et al. (2015).”
- Evaluating Lossy Compression Rates of Deep Generative Models (2020, methodology): “4b), we experimented with different GAN models such as DCGAN (Rad-ford et al., 2015), DCGAN with Gradient Penalty (GP-GAN) (Gulrajani et al., 2017), Spectral Normalization (SN-GAN) (Miyato et al., 2018), and DCGAN with Binarized Representation Entropy Regularization (BRE-GAN) (Cao et al., 2018).”
- Your GAN is Secretly an Energy-based Model and You Should use Discriminator Driven Latent Sampling (2020, methodology): “For CelebA dataset, we adopt DCGAN and WGAN as the baseline model following the same setting in [64].”
- Flow Contrastive Estimation of Energy-Based Models (2019, methodology): “Specifically, following the same procedure outlined in [58], the features from the top three convolutional layers are max pooled and concatenated to form a 14, 336dimensional vector of feature.”
- Learning Non-Convergent Non-Persistent Short-Run MCMC Toward Energy-Based Model (2019, neutral): “0440 DCGAN [38] 0.”
- Large Scale GAN Training for High Fidelity Natural Image Synthesis (2018, methodology): “02I) (Radford et al., 2016) or Xavier initialization (Glorot & Bengio, 2010).”
- Autoregressive Quantile Networks for Generative Modeling (2018, background): “Much of the recent research on GANs has been focused on improving stability (Radford et al., 2015; Arjovsky et al., 2017; Daskalakis et al., 2017) and sample diversity (Gul-rajani et al., 2017; Salimans et al., 2016; 2018).”