mlsanityData to 7 Oct 2026

Rebooting ACGAN: Auxiliary Classifier GANs with Stable Training

arXiv 2111.01118 ↗First posted 1 Nov 2021cs.CV cs.AI cs.LGcited by 57

Not on the map. Why?

Abstract (arXiv)

Conditional Generative Adversarial Networks (cGAN) generate realistic images by incorporating class information into GAN. While one of the most popular cGANs is an auxiliary classifier GAN with softmax cross-entropy loss (ACGAN), it is widely known that training ACGAN is challenging as the number of classes in the dataset increases. ACGAN also tends to generate easily classifiable samples with a lack of diversity. In this paper, we introduce two cures for ACGAN. First, we identify that gradient exploding in the classifier can cause an undesirable collapse in early training, and projecting input vectors onto a unit hypersphere can resolve the problem. Second, we propose the Data-to-Data Cross-Entropy loss (D2D-CE) to exploit relational information in the class-labeled dataset. On this foundation, we propose the Rebooted Auxiliary Classifier Generative Adversarial Network (ReACGAN). The experimental results show that ReACGAN achieves state-of-the-art generation results on CIFAR10, Tiny-ImageNet, CUB200, and ImageNet datasets. We also verify that ReACGAN benefits from differentiable augmentations and that D2D-CE harmonizes with StyleGAN2 architecture. Model weights and a software package that provides implementations of representative cGANs and all experiments in our paper are available at https://github.com/POSTECH-CVLab/PyTorch-StudioGAN.

Key facts. Cited by 57 papers in the map (data through 7 Oct 2026). Builds on 59 of its 85 references that are in the map. First posted on arXiv 1 Nov 2021.

Builds on

59 of 85 references.

References · 59

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  3. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  4. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  5. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
  6. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,712
  7. 2021Improved Denoising Diffusion Probabilistic Modelscited by 3,736
  8. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
  9. 2016Improved Techniques for Training GANscited by 2,938
  10. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,609
  11. 2017Improved Training of Wasserstein GANscited by 2,223
  12. 2014Conditional Generative Adversarial Netscited by 2,152
38 more
  1. 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,048
  2. 2018Spectral Normalization for Generative Adversarial Networkscited by 1,618
  3. 2020Training Generative Adversarial Networks with Limited Datacited by 1,184
  4. 2017Mixed Precision Trainingcited by 1,135
  5. 2019StarGAN v2: Diverse Image Synthesis for Multiple Domainscited by 1,095
  6. 2016Least Squares Generative Adversarial Networkscited by 1,000
  7. 2019Improved Precision and Recall Metric for Assessing Generative Modelscited by 925
  8. 2018Self-Attention Generative Adversarial Networkscited by 809
  9. 2017Wasserstein GANcited by 635
  10. 2020Contrastive Learning with Hard Negative Samplescited by 619
  11. 2016Conditional Image Synthesis With Auxiliary Classifier GANscited by 562
  12. 2016f-GAN: Training Generative Neural Samplers using Variational Divergence Minimizationcited by 504
  13. 2017Towards Principled Methods for Training Generative Adversarial Networkscited by 460
  14. 2020Reliable Fidelity and Diversity Metrics for Generative Modelscited by 425
  15. 2020Closed-Form Factorization of Latent Semantics in GANscited by 407
  16. 2018Assessing Generative Models via Precision and Recallcited by 401
  17. 2017DeblurGAN: Blind Motion Deblurring Using Conditional Adversarial Networkscited by 366
  18. 2020Differentiable Augmentation for Data-Efficient GAN Trainingcited by 361
  19. 2020Debiased Contrastive Learningcited by 354
  20. 2016A Learned Representation For Artistic Stylecited by 340
  21. 2018cGANs with Projection Discriminatorcited by 253
  22. 2017Geometric GANcited by 232
  23. 2019Few-Shot Unsupervised Image-to-Image Translationcited by 222
  24. 2017VEEGAN: Reducing Mode Collapse in GANs using Implicit Variational Learningcited by 199
  25. 2020A Self-supervised Approach for Adversarial Robustnesscited by 180
  26. 2017Modulating early visual processing by languagecited by 167
  27. 2018FairGAN: Fairness-aware Generative Adversarial Networkscited by 164
  28. 2020Two-branch Recurrent Network for Isolating Deepfakes in Videoscited by 161
  29. 2016Semantic Image Inpainting with Deep Generative Modelscited by 156
  30. 2019Classification Accuracy Score for Conditional Generative Modelscited by 134
  31. 2019Consistency Regularization for Generative Adversarial Networkscited by 134
  32. 2020Freeze the Discriminator: a Simple Baseline for Fine-Tuning GANscited by 132
  33. 2020Boosting Contrastive Self-Supervised Learning with False Negative Cancellationcited by 119
  34. 2019Deep Learning for Deepfakes Creation and Detection: A Surveycited by 102
  35. 2018SketchyGAN: Towards Diverse and Realistic Sketch to Image Synthesiscited by 81
  36. 2018The Unusual Effectiveness of Averaging in GAN Trainingcited by 73
  37. 2020Your GAN is Secretly an Energy-based Model and You Should use Discriminator Driven Latent Samplingcited by 71
  38. 2020Improved Consistency Regularization for GANscited by 67

50 most cited of 59 All 59 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 9; 2023: 19; 2024: 12; 2025: 12; 2026: 4.

57 papers.

Sort:

By area:

  1. 2023Scaling up GANs for Text-to-Image Synthesiscited by 492
  2. 2023Consistency Trajectory Models: Learning Probability Flow ODE Trajectory of Diffusioncited by 448
  3. 2023Exposing flaws of generative model evaluation metrics and their unfair treatment of diffusion modelscited by 199
  4. 2024Distilling Diffusion Models into Conditional GANscited by 78
  5. 2022The ArtBench Dataset: Benchmarking Generative Models with Artworkscited by 64
  6. 2023Better Generative Replay for Continual Federated Learningcited by 53
  7. 2022StudioGAN: A Taxonomy and Benchmark of GANs for Image Synthesiscited by 38
  8. 2023Ultra-High-Resolution Detector Simulation with Intra-Event Aware GAN and Self-Supervised Relational Reasoningcited by 25
  9. 2023Cousins Of The Vendi Score: A Family Of Similarity-Based Diversity Metrics For Science And Machine Learningcited by 24
  10. 2024Continuous-Multiple Image Outpainting in One-Step via Positional Query and A Diffusion-based Approachcited by 18
  11. 2023Guiding Energy-based Models via Contrastive Latent Variablescited by 17
  12. 2024An Interpretable Evaluation of Entropy-based Novelty of Generative Modelscited by 17
38 more
  1. 2023NoisyTwins: Class-Consistent and Diverse Image Generation through StyleGANscited by 12
  2. 2024Expensive Multi-Objective Bayesian Optimization Based on Diffusion Modelscited by 10
  3. 2024CCDM: Continuous Conditional Diffusion Models for Image Generationcited by 8
  4. 2024Scalable Surrogate Verification of Image-based Neural Network Control Systems using Composition and Unrollingcited by 8
  5. 2022Don't Be So Dense: Sparse-to-Sparse GAN Training Without Sacrificing Performancecited by 7
  6. 20243D Priors-Guided Diffusion for Blind Face Restorationcited by 7
  7. 2023Preconditioned Score-based Generative Modelscited by 6
  8. 2024GenFormer -- Generated Images are All You Need to Improve Robustness of Transformers on Small Datasetscited by 6
  9. 2025The Vendiscope: An Algorithmic Microscope For Data Collectionscited by 5
  10. 2025One-Way Ticket:Time-Independent Unified Encoder for Distilling Text-to-Image Diffusion Modelscited by 5
  11. 2022Transfer Learning with Pre-trained Conditional Generative Modelscited by 4
  12. 2022Generative Adversarial Networks and Image-Based Malware Classificationcited by 4
  13. 2025Synergy Between Sufficient Changes and Sparse Mixing Procedure for Disentangled Representation Learningcited by 4
  14. 2022Revisiting GANs by Best-Response Constraint: Perspective, Methodology, and Applicationcited by 3
  15. 2022Design What You Desire: Icon Generation from Orthogonal Application and Theme Labelscited by 3
  16. 2023Stable and Consistent Prediction of 3D Characteristic Orientation via Invariant Residual Learningcited by 3
  17. 2023Turning Waste into Wealth: Leveraging Low-Quality Samples for Enhancing Continuous Conditional Generative Adversarial Networkscited by 3
  18. 2024GANs Conditioning Methods: A Surveycited by 3
  19. 2021Putting 3D Spatially Sparse Networks on a Dietcited by 2
  20. 2023GREAT Score: Global Robustness Evaluation of Adversarial Perturbation using Generative Modelscited by 2
  21. 2023Spider GAN: Leveraging Friendly Neighbors to Accelerate GAN Trainingcited by 2
  22. 2023NaturalFinger: Generating Natural Fingerprint with Generative Adversarial Networkscited by 2
  23. 2023Anomaly Score: Evaluating Generative Models and Individual Generated Images based on Complexity and Vulnerabilitycited by 2
  24. 2024CHAIN: Enhancing Generalization in Data-Efficient GANs via lipsCHitz continuity constrAIned Normalizationcited by 2
  25. 20233D GANs and Latent Space: A comprehensive surveycited by 1
  26. 2023DuDGAN: Improving Class-Conditional GANs via Dual-Diffusioncited by 1
  27. 2024MCGAN: Enhancing GAN Training with Regression-Based Generator Losscited by 1
  28. 2025Beyond a Single Mode: GAN Ensembles for Diverse Medical Data Generationcited by 1
  29. 2025Enhanced Generative Model Evaluation with Clipped Density and Coveragecited by 1
  30. 2022Continuous Facial Motion Deblurringcited by 0
  31. 2022Cyclegan Network for Sheet Metal Welding Drawing Translationcited by 0
  32. 2023Contrastive Bi-Projector for Unsupervised Domain Adaptioncited by 0
  33. 2023Class Conditional Time Series Generation with Structured Noise Space GANcited by 0
  34. 2024Intriguing Properties of Modern GANscited by 0
  35. 2025An Integrated Approach to AI-Generated Content in e-healthcited by 0
  36. 2025Conditional Deep Generative Models for Belief State Planningcited by 0
  37. 2025Bringing Balance to Hand Shape Classification: Mitigating Data Imbalance Through Generative Modelscited by 0
  38. 2025Imbalance-Robust and Sampling-Efficient Continuous Conditional GANs via Adaptive Vicinal Learning and Auxiliary Regularizationcited by 0

50 most cited of 57 All 57 (JSON)