TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Methods/LSGAN

LSGAN

Computer VisionIntroduced 200018 papers
Source Paper

Description

LSGAN, or Least Squares GAN, is a type of generative adversarial network that adopts the least squares loss function for the discriminator. Minimizing the objective function of LSGAN yields minimizing the Pearson χ2\chi^{2}χ2 divergence. The objective function can be defined as:

min⁡_DV_LSGAN(D)=12E_x∼p_data(x)[(D(x)−b)2]+12E_z∼p_z(z)[(D(G(z))−a)2]\min\_{D}V\_{LSGAN}\left(D\right) = \frac{1}{2}\mathbb{E}\_{\mathbf{x} \sim p\_{data}\left(\mathbf{x}\right)}\left[\left(D\left(\mathbf{x}\right) - b\right)^{2}\right] + \frac{1}{2}\mathbb{E}\_{\mathbf{z}\sim p\_{\mathbf{z}}\left(\mathbf{z}\right)}\left[\left(D\left(G\left(\mathbf{z}\right)\right) - a\right)^{2}\right]min_DV_LSGAN(D)=21​E_x∼p_data(x)[(D(x)−b)2]+21​E_z∼p_z(z)[(D(G(z))−a)2]

min⁡_GV_LSGAN(G)=12E_z∼p_z(z)[(D(G(z))−c)2]\min\_{G}V\_{LSGAN}\left(G\right) = \frac{1}{2}\mathbb{E}\_{\mathbf{z} \sim p\_{\mathbf{z}}\left(\mathbf{z}\right)}\left[\left(D\left(G\left(\mathbf{z}\right)\right) - c\right)^{2}\right]min_GV_LSGAN(G)=21​E_z∼p_z(z)[(D(G(z))−c)2]

where aaa and bbb are the labels for fake data and real data and ccc denotes the value that GGG wants DDD to believe for fake data.

Papers Using This Method

Low-light Enhancement Method Based on Attention Map Net2022-08-19GM Score: Incorporating inter-class and intra-class generator diversity, discriminability of disentangled representation, and sample fidelity for evaluating GANs2021-12-13Generative Adversarial Networks and Adversarial Autoencoders: Tutorial and Survey2021-11-26A Closer Look at Fourier Spectrum Discrepancies for CNN-generated Images Detection2021-03-31Improve GAN-based Neural Vocoder using Pointwise Relativistic LeastSquare GAN2021-03-26PriorGAN: Real Data Prior for Generative Adversarial Nets2020-06-30Towards a Neural Graphics Pipeline for Controllable Image Generation2020-06-18FastSpeech 2: Fast and High-Quality End-to-End Text to Speech2020-06-08Least $k$th-Order and Rényi Generative Adversarial Networks2020-06-03Identity-Preserving Realistic Talking Face Generation2020-05-25A Study into Echocardiography View Conversion2019-12-05RankGAN: A Maximum Margin Ranking GAN for Generating Faces2018-12-19GANs beyond divergence minimization2018-09-06The relativistic discriminator: a key element missing from standard GAN2018-07-02Tempered Adversarial Networks2018-02-12On the Effectiveness of Least Squares Generative Adversarial Networks2017-12-18Deep Generative Adversarial Networks for Compressed Sensing Automates MRI2017-05-31Least Squares Generative Adversarial Networks2016-11-13