Data to 14 Oct 2026

Least Squares Generative Adversarial Networks

arXiv 1611.04076 ↗First posted 13 Nov 2016cs.CVcited by 1,001

Not on the map. Why?

Cited by 51 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Unsupervised learning with generative adversarial networks (GANs) has proven hugely successful. Regular GANs hypothesize the discriminator as a classifier with the sigmoid cross entropy loss function. However, we found that this loss function may lead to the vanishing gradients problem during the learning process. To overcome such a problem, we propose in this paper the Least Squares Generative Adversarial Networks (LSGANs) which adopt the least squares loss function for the discriminator. We show that minimizing the objective function of LSGAN yields minimizing the Pearson chi2 divergence. There are two benefits of LSGANs over regular GANs. First, LSGANs are able to generate higher quality images than regular GANs. Second, LSGANs perform more stable during the learning process. We evaluate LSGANs on five scene datasets and the experimental results show that the images generated by LSGANs are of better quality than the ones generated by regular GANs. We also conduct two comparison experiments between LSGANs and regular GANs to illustrate the stability of LSGANs.

Key facts. Cited by 1,001 papers in the map (data through 14 Oct 2026). First posted on arXiv 13 Nov 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2018: 1; 2019: 1; 2020: 1; 2021: 299; 2022: 244; 2023: 191; 2024: 108; 2025: 95; 2026: 61.

1,001 papers.

Sort:

By area:

2022Generative Adversarial Networkscited by 5,627
2024Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Modelscited by 557
2022Improving Diffusion Models for Inverse Problems using Manifold Constraintscited by 508
2021Deep Marching Tetrahedra: a Hybrid Representation for High-Resolution 3D Shape Synthesiscited by 460
2022Detecting Deepfakes with Self-Blended Imagescited by 338
2021VITON-HD: High-Resolution Virtual Try-On via Misalignment-Aware Normalizationcited by 287
2022Brain Imaging Generation with Latent Diffusion Modelscited by 268
2021Cross-Modal Contrastive Learning for Text-to-Image Generationcited by 259
2021Deep Generative Modelling: A Comparative Review of VAEs, GANs, Normalizing Flows, Energy-Based and Autoregressive Modelscited by 252
2022BigVGAN: A Universal Neural Vocoder with Large-Scale Trainingcited by 251
2023Diff-Instruct: A Universal Approach for Transferring Knowledge From Pre-trained Diffusion Modelscited by 236
2021Robust Motion In-betweeningcited by 229

38 more

2023A Comprehensive Survey of AI-Generated Content (AIGC): A History of Generative AI from GAN to ChatGPTcited by 224
2022CDDFuse: Correlation-Driven Dual-Branch Feature Decomposition for Multi-Modality Image Fusioncited by 223
2021Neural-PIL: Neural Pre-Integrated Lighting for Reflectance Decompositioncited by 205
2021A Survey on Neural Speech Synthesiscited by 184
2022Depth-Aware Generative Adversarial Network for Talking Head Video Generationcited by 178
2021TransGAN: Two Pure Transformers Can Make One Strong GAN, and That Can Scale Upcited by 162
2023DDFM: Denoising Diffusion Model for Multi-Modality Image Fusioncited by 153
2021StyleSwin: Transformer-based GAN for High-resolution Image Generationcited by 152
2022NaturalSpeech: End-to-End Text to Speech Synthesis with Human-Level Qualitycited by 152
2023StyleTTS 2: Towards Human-Level Text-to-Speech through Style Diffusion and Adversarial Training with Large Speech Language Modelscited by 152
2022Reconstructing Training Data with Informed Adversariescited by 148
2022StyleGAN-Human: A Data-Centric Odyssey of Human Generationcited by 144
2022High-Resolution Virtual Try-On with Misalignment and Occlusion-Handled Conditionscited by 130
2021Image-to-Image Translation: Methods and Applicationscited by 116
2021Learning Debiased Representation via Disentangled Feature Augmentationcited by 116
2021Beyond Self-attention: External Attention using Two Linear Layers for Visual Taskscited by 109
2021Regularizing Generative Adversarial Networks under Limited Datacited by 107
2021MeGA-CDA: Memory Guided Attention for Category-Aware Unsupervised Domain Adaptive Object Detectioncited by 106
2021Recent advances and clinical applications of deep learning in medical image analysiscited by 104
2021Meta-StyleSpeech : Multi-Speaker Adaptive Text-to-Speech Generationcited by 93
2021Aggregated Contextual Transformations for High-Resolution Image Inpaintingcited by 89
2021PoseAug: A Differentiable Pose Augmentation Framework for 3D Human Pose Estimationcited by 89
2022Adversarial Motion Priors Make Good Substitutes for Complex Reward Functionscited by 89
2021Ensembling Off-the-shelf Models for GAN Trainingcited by 86
2021Equivariant Imaging: Learning Beyond the Range Spacecited by 83
2022Learning to generate line drawings that convey geometry and semanticscited by 83
2021Generative Modeling with Optimal Transport Mapscited by 82
2021DANNet: A One-Stage Domain Adaptation Network for Unsupervised Nighttime Semantic Segmentationcited by 80
2022FreeVC: Towards High-Quality Text-Free One-Shot Voice Conversioncited by 80
2022An Introduction to Neural Data Compressioncited by 79
2021CLIP2StyleGAN: Unsupervised Extraction of StyleGAN Edit Directionscited by 78
2023DINet: Deformation Inpainting Network for Realistic Face Visually Dubbing on High Resolution Videocited by 74
2022Unsupervised Night Image Enhancement: When Layer Decomposition Meets Light-Effects Suppressioncited by 73
2021A Closer Look at Fourier Spectrum Discrepancies for CNN-generated Images Detectioncited by 68
2021Dual Contrastive Learning for Unsupervised Image-to-Image Translationcited by 66
2023BlendFace: Re-designing Identity Encoders for Face-Swappingcited by 66
2021GANs for Medical Image Synthesis: An Empirical Studycited by 65
2021Image-to-image Translation via Hierarchical Style Disentanglementcited by 63

50 most cited of 1,001 All 1,001 (JSON)