Black-Box Diagnosis and Calibration on GAN Intra-Mode Collapse: A Pilot Study
Not on the map. Why?
Abstract (arXiv)
Generative adversarial networks (GANs) nowadays are capable of producing images of incredible realism. One concern raised is whether the state-of-the-art GAN's learned distribution still suffers from mode collapse, and what to do if so. Existing diversity tests of samples from GANs are usually conducted qualitatively on a small scale, and/or depends on the access to original training data as well as the trained model parameters. This paper explores to diagnose GAN intra-mode collapse and calibrate that, in a novel black-box setting: no access to training data, nor the trained model parameters, is assumed. The new setting is practically demanded, yet rarely explored and significantly more challenging. As a first stab, we devise a set of statistical tools based on sampling, that can visualize, quantify, and rectify intra-mode collapse. We demonstrate the effectiveness of our proposed diagnosis and calibration techniques, via extensive simulations and experiments, on unconditional GAN image generation (e.g., face and vehicle). Our study reveals that the intra-mode collapse is still a prevailing problem in state-of-the-art GANs and the mode collapse is diagnosable and calibratable in black-box settings. Our codes are available at: https://github.com/VITA-Group/BlackBoxGANCollapse.
Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 55 of its 82 references that are in the map. First posted on arXiv 23 Jul 2021.
Builds on
55 of 82 references.
References · 55
- 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,415
- 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
- 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
- 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,967
- 2016Improved Techniques for Training GANscited by 2,938
- 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,609
- 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,048
- 2018Spectral Normalization for Generative Adversarial Networkscited by 1,618
- 2015LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loopcited by 1,350
- 2016Least Squares Generative Adversarial Networkscited by 1,000
- 2019EnlightenGAN: Deep Light Enhancement without Paired Supervisioncited by 466
- 2019DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Bettercited by 361
38 more
- 2016NIPS 2016 Tutorial: Generative Adversarial Networkscited by 284
- 2018Improving fairness in machine learning systems: What do industry practitioners need?cited by 262
- 2018Differentially Private Generative Adversarial Networkcited by 235
- 2017StackGAN++: Realistic Image Synthesis with Stacked Generative Adversarial Networkscited by 229
- 2018A Note on the Inception Scorecited by 225
- 2018Pros and Cons of GAN Evaluation Measurescited by 224
- 2016Coupled Generative Adversarial Networkscited by 216
- 2016Unrolled Generative Adversarial Networkscited by 208
- 2017VEEGAN: Reducing Mode Collapse in GANs using Implicit Variational Learningcited by 199
- 2018FairGAN: Fairness-aware Generative Adversarial Networkscited by 164
- 2019RetinaFace: Single-stage Dense Face Localisation in the Wildcited by 164
- 2019Seeing What a GAN Cannot Generatecited by 148
- 2020REVISE: A Tool for Measuring and Mitigating Bias in Visual Datasetscited by 136
- 2016Mode Regularized Generative Adversarial Networkscited by 123
- 2017PacGAN: The power of two samples in generative adversarial networkscited by 104
- 2019AutoGAN: Neural Architecture Search for Generative Adversarial Networkscited by 94
- 2020Learning Attentive Pairwise Interaction for Fine-Grained Classificationcited by 84
- 2016Generative Multi-Adversarial Networkscited by 60
- 2017Multi-Agent Diverse Generative Adversarial Networkscited by 59
- 2018Towards Privacy-Preserving Visual Recognition via Adversarial Training: A Pilot Studycited by 48
- 2018Discriminator Rejection Samplingcited by 48
- 2019Controllable Artistic Text Style Transfer via Shape-Matching GANcited by 45
- 2019Detecting Overfitting of Deep Generative Networks via Latent Recoverycited by 44
- 2020GAN Slimming: All-in-One GAN Compression by A Unified Optimization Frameworkcited by 44
- 2018Metropolis-Hastings Generative Adversarial Networkscited by 40
- 2020Deep Plastic Surgery: Robust and Controllable Image Editing with Human-Drawn Sketchescited by 37
- 2018An Introduction to Image Synthesis with Generative Adversarial Netscited by 32
- 2018Fairness GANcited by 32
- 2018RAM: A Region-Aware Deep Model for Vehicle Re-Identificationcited by 30
- 2019All-In-One Underwater Image Enhancement using Domain-Adversarial Learningcited by 29
- 2017Do GANs actually learn the distribution? An empirical studycited by 23
- 2019Delving into Robust Object Detection from Unmanned Aerial Vehicles: A Deep Nuisance Disentanglement Approachcited by 22
- 2018DADA: Deep Adversarial Data Augmentation for Extremely Low Data Regime Classificationcited by 18
- 2018Stacked Dense U-Nets with Dual Transformers for Robust Face Alignmentcited by 17
- 2019Attributes Guided Feature Learning for Vehicle Re-identificationcited by 12
- 2018Efficient Facial Representations for Age, Gender and Identity Recognition in Organizing Photo Albums using Multi-output CNNcited by 10
- 2020PCAL: A Privacy-preserving Intelligent Credit Risk Modeling Framework Based on Adversarial Learningcited by 7
- 2018Pixel Level Data Augmentation for Semantic Image Segmentation using Generative Adversarial Networkscited by 6
50 most cited of 55 All 55 (JSON)
Built on by
Citing papers per year: 2022: 1; 2023: 0; 2024: 0; 2025: 2.
3 papers.