The DOI matches its Crossref record; 64 of the 64 references it cites were found in a registry or an index.
On Aliased Resizing and Surprising Subtleties in GAN Evaluation
Open accessAbstract
Metrics for evaluating generative models aim to measure the discrepancy between real and generated images. The often-used Fréchet Inception Distance (FID) metric, for example, extracts “high-level” features using a deep network from the two sets. However, we find that the differences in “low-level” preprocessing, specifically image resizing and compression, can induce large variations and have unforeseen consequences. For instance, when resizing an image, e.g., with a bilinear or bicubic kernel, signal processing principles mandate adjusting prefilter width depending on the downsampling factor, to antialias to the appropriate bandwidth. However, commonly-used implementations use a fixed-width prefilter, resulting in aliasing artifacts. Such aliasing leads to corruptions in the feature extraction down-stream. Next, lossy compression, such as JPEG, is commonly used to reduce the file size of an image. Although designed to minimally degrade the perceptual quality of an image, the operation also produces variations downstream. Furthermore, we show that if compression is used on real training images, FID can actually improve if the generated images are also subsequently compressed. This paper shows that choices in low-level image processing have been an under-appreciated aspect of generative modeling. We identify and characterize variations in generative modeling development pipelines, provide recommendations based on signal processing principles, and release a reference implementation to facilitate future comparisons.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
ImageNet: A large-scale hierarchical image database
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206848 · Cited by 65,333
Gradient-based learning applied to document recognition
Lecun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998) · Proceedings of the IEEE · doi:10.1109/5.726791 · Cited by 58,805
Rethinking the Inception Architecture for Computer Vision
Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., & Wojna, Z. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.308 · Cited by 32,138
Unpaired image-to-image translation using cycle-consistent adversarial networks
Zhu, J.-Y., Park, T., Isola, P., & Efros, A. A. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.244 · Cited by 23,602
Self-citationAuto-Encoding Variational Bayes
Kingma, D. P., & Welling, M. (2013) · arXiv · doi:10.48550/arxiv.1312.6114 · Cited by 20,067
Labaca-Castro, R. (2023) · Machine Learning under Malware Attack · doi:10.1007/978-3-658-40442-0_9 · Cited by 19,272
MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
Howard, A. G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., Andreetto, M., & Adam, H. (2017) · arXiv · doi:10.48550/arxiv.1704.04861 · Cited by 19,015
The Unreasonable Effectiveness of Deep Features as a Perceptual Metric
Zhang, R., Isola, P., Efros, A. A., Shechtman, E., & Wang, O. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00068 · Cited by 14,623
Self-citationUnsupervised representation learning with deep convolutional generative adversarial networks
Radford, A., Metz, L., & Chintala, S. (2015) · arXiv · doi:10.48550/arxiv.1511.06434 · Cited by 12,235
A Style-Based Generator Architecture for Generative Adversarial Networks
Karras, T., Laine, S., & Aila, T. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00453 · Cited by 11,714
Perceptual Losses for Real-Time Style Transfer and Super-Resolution
Johnson, J., Alahi, A., & Fei-Fei, L. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46475-6_43 · Cited by 11,283
GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., & Hochreiter, S. (2017) · arXiv · doi:10.48550/arxiv.1706.08500 · Cited by 8,365
Improved Techniques for Training GANs
Salimans, T., Goodfellow, I., Zaremba, W., Cheung, V., Radford, A., & Chen, X. (2016) · arXiv · doi:10.48550/arxiv.1606.03498 · Cited by 6,965
Analyzing and Improving the Image Quality of StyleGAN
Karras, T., Laine, S., Aittala, M., Hellsten, J., Lehtinen, J., & Aila, T. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00813 · Cited by 6,332
Image Style Transfer Using Convolutional Neural Networks
Gatys, L. A., Ecker, A. S., & Bethge, M. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.265 · Cited by 6,025
Discrete-time Signal Processing
Williamson, D. (1999) · Advanced Textbooks in Control and Signal Processing · doi:10.1007/978-1-4471-0541-1 · Cited by 4,858
Digital Image Processing: PIKS Inside
Pratt, W. K. (2002) · Wiley eBooks · doi:10.1002/0471221325 · Cited by 4,340
Computer vision: algorithms and applications
(2011) · Choice Reviews Online · doi:10.5860/choice.48-5140 · Cited by 3,911
Computer Vision: A Modern Approach
Forsyth, D. A., & Ponce, J. (2002) · Cited by 3,739
Large Scale GAN Training for High Fidelity Natural Image Synthesis
Brock, A., Donahue, J., & Simonyan, K. (2018) · arXiv · doi:10.48550/arxiv.1809.11096 · Cited by 3,717
Cubic convolution interpolation for digital image processing
Keys, R. (1981) · IEEE Transactions on Acoustics, Speech, and Signal Processing · doi:10.1109/tassp.1981.1163711 · Cited by 3,255
Certain Topics in Telegraph Transmission Theory
Nyquist, H. (1928) · Transactions of the American Institute of Electrical Engineers · doi:10.1109/t-aiee.1928.5055024 · Cited by 3,089
Semantic Image Synthesis With Spatially-Adaptive Normalization
Park, T., Liu, M.-Y., Wang, T.-C., & Zhu, J.-Y. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00244 · Cited by 2,974
Self-citationThe JPEG still picture compression standard
Wallace, G. K. (1992) · IEEE Transactions on Consumer Electronics · doi:10.1109/30.125072 · Cited by 2,851
Multimodal Unsupervised Image-to-Image Translation
Huang, X., Liu, M.-Y., Belongie, S., & Kautz, J. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01219-9_11 · Cited by 2,451
Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fields
Barron, J. T., Mildenhall, B., Tancik, M., Hedman, P., Martin-Brualla, R., & Srinivasan, P. P. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00580 · Cited by 1,921
Salakhutdinov, R., & Hinton, G. E. (2009) · International Conference on Artificial Intelligence and Statistics · Cited by 1,890
Conditional Image Generation with PixelCNN Decoders
van den Oord, A., Kalchbrenner, N., Vinyals, O., Espeholt, L., Graves, A., & Kavukcuoglu, K. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1606.05328 · Cited by 1,833
Learning from Simulated and Unsupervised Images through Adversarial Training
Shrivastava, A., Pfister, T., Tuzel, O., Susskind, J., Wang, W., & Webb, R. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.241 · Cited by 1,814
StarGAN v2: Diverse Image Synthesis for Multiple Domains
Choi, Y., Uh, Y., Yoo, J., & Ha, J.-W. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00821 · Cited by 1,663
Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networks
Denton, E., Chintala, S., Szlam, A. D., & Fergus, R. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1506.05751 · Cited by 1,541
Evaluation of Pooling Operations in Convolutional Architectures for Object Recognition
Scherer, D., Müller, A., & Behnke, S. (2010) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-15825-4_10 · Cited by 1,503
Benchmarking Neural Network Robustness to Common Corruptions and Perturbations
Hendrycks, D., & Dietterich, T. (2019) · arXiv · doi:10.48550/arxiv.1903.12261 · Cited by 1,335
LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop
Yu, F., Seff, A., Zhang, Y., Song, S., Funkhouser, T., & Xiao, J. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1506.03365 · Cited by 1,245
Training Generative Adversarial Networks with Limited Data
Karras, T., Aittala, M., Hellsten, J., Laine, S., Lehtinen, J., & Aila, T. (2020) · arXiv · doi:10.48550/arxiv.2006.06676 · Cited by 1,170
A note on the evaluation of generative models
Theis, L., Oord, A. V. D., & Bethge, M. (2015) · arXiv · doi:10.48550/arxiv.1511.01844 · Cited by 1,026
Pros and cons of GAN evaluation measures
Borji, A. (2019) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2018.10.009 · Cited by 963
Testing Statistical Hypotheses
Neath, A. A. (2006) · Journal of the American Statistical Association · doi:10.1198/jasa.2006.s100 · Cited by 948
Auto-Encoding Variational Bayes
Chen, Y., Liu, J., Peng, L., Wu, Y., Xu, Y., & Zhang, Z. (2024) · Cambridge Explorations in Arts and Sciences · doi:10.61603/ceas.v2i1.33 · Cited by 934
Alias-Free Generative Adversarial Networks
Karras, T., Aittala, M., Laine, S., Härkönen, E., Hellsten, J., Lehtinen, J., & Aila, T. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2106.12423 · Cited by 840
Computer graphics: Principles and practice
Carter, M. P. (1997) · Color Research & Application · doi:10.1002/(sici)1520-6378(199702)22:1<65::aid-col11>3.0.co;2-7 · Cited by 814
Generating diverse high-fidelity images with vq-vae-2
Razavi, A., Oord, A. V. D., & Vinyals, O. (2019) · arXiv · doi:10.48550/arxiv.1906.00446 · Cited by 709 · cited 2×
“A wide range of image and video synthesis applications [41, 50, 61, 77] have been enabled, as a result of tremendous progress in deep generative models such as GANs [7, 24, 30, 33, 54], VAEs [37, 51, 56], autoregressive models [48], flow-based models [14, 36], and energy-based models [17, 46, 58].”
BackgroundFew-Shot Unsupervised Image-to-Image Translation
Liu, M.-Y., Huang, X., Mallya, A., Karras, T., Aila, T., Lehtinen, J., & Kautz, J. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.01065 · Cited by 646
Introduction to Computer Graphics
Foley, J. D., Phillips, R. L., Hughes, J. F., van Dam, A., & Feiner, S. (1993) · CERN Document Server (European Organization for Nuclear Research) · Cited by 543
GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
Bynagari, N. B. (2019) · Asian Journal of Applied Science and Engineering · doi:10.18034/ajase.v8i1.9 · Cited by 513
Why do deep convolutional networks generalize so poorly to small image transformations?
Azulay, A., & Weiss, Y. (2018) · arXiv · doi:10.48550/arxiv.1805.12177 · Cited by 428 · cited 1×
“Despite these advances, generative methods continue to be detectable [8, 68], and discriminative networks continue to be sensitive to small perturbations, such as shifts [2, 18] and JPEG compression [25].”
BackgroundMaking Convolutional Networks Shift-Invariant Again
Zhang, R. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1904.11486 · Cited by 420
Self-citationImproved Precision and Recall Metric for Assessing Generative Models
Kynkäänniemi, T., Karras, T., Laine, S., Lehtinen, J., & Aila, T. (2019) · arXiv · doi:10.48550/arxiv.1904.06991 · Cited by 379
What Makes Fake Images Detectable? Understanding Properties that Generalize
Chai, L., Bau, D., Lim, S.-N., & Isola, P. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58574-7_7 · Cited by 357
Revisiting Classifier Two-Sample TestsPreprint
López-Paz, D., & Oquab, M. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1610.06545 · Cited by 353
Large Scale Adversarial Representation Learning
Donahue, J., & Simonyan, K. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1907.02544 · Cited by 351
(2017) · doi:10.48550/arxiv.1712.02779 · Cited by 300
Rigid-Motion Scattering for Texture Classification
Sifre, L., & Mallat, S. (2014) · arXiv (Cornell University) · doi:10.48550/arxiv.1403.1687 · Cited by 272
Effectively Unbiased FID and Inception Score and Where to Find Them
Chong, M. J., & Forsyth, D. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00611 · Cited by 242
Measuring Robustness to Natural Distribution Shifts in Image Classification
Taori, R., Dave, A., Shankar, V., Carlini, N., Recht, B., & Schmidt, L. (2020) · arXiv · doi:10.48550/arxiv.2007.00644 · Cited by 206
Classification Accuracy Score for Conditional Generative ModelsPreprint
Ravuri, S. V., & Vinyals, O. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1905.10887 · Cited by 179
Do GANs actually learn the distribution? An empirical studyPreprint
Arora, S., & Zhang, Y. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1706.08224 · Cited by 177
Delving Deeper into Anti-Aliasing in ConvNets
Zou, X., Xiao, F., Yu, Z., Li, Y., & Lee, Y. J. (2022) · International Journal of Computer Vision · doi:10.1007/s11263-022-01672-y · Cited by 138
On the Anatomy of MCMC-Based Maximum Likelihood Learning of Energy-Based Models
Nijkamp, E., Hill, M., Han, T., Zhu, S. C., & Wu, Y. N. (2020) · AAAI Publications (The Association for the Advancement of Artificial Intelligence (AAAI)) · doi:10.1609/aaai.v34i04.5973 · Cited by 117
Dual Contradistinctive Generative Autoencoder
Parmar, G., Li, D., Lee, K., & Tu, Z. (2021) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr46437.2021.00088 · Cited by 112
Self-citationDiverse Image Generation via Self-Conditioned GANs
Liu, S., Wang, T., Bau, D., Zhu, J.-Y., & Torralba, A. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.01429 · Cited by 91
Self-citationZhu, S. C., Yuille, A., & Mumford, D. B. (2000) · International Journal of Computer Vision · doi:10.1023/a:1026531017760 · Cited by 86
(2019) · USENIX Security Symposium · Cited by 60
Adversarial Preprocessing: Understanding and Preventing Image-Scaling Attacks in Machine Learning.
Quiring, E., Klein, D. A., Arp, D. J., Johns, M., & Rieck, K. (2020) · USENIX Security Symposium · Cited by 41
Cited by
Scalable Diffusion Models with Transformers
Peebles, W., & Xie, S. (2023) · 2023 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.00387 · Cited by 2,284
Scalable Diffusion Models with Transformers
Peebles, W., & Xie, S. (2022) · arXiv · doi:10.48550/arxiv.2212.09748 · Cited by 2,284
Compositional Visual Generation with Composable Diffusion Models
Liu, N., Li, S., Du, Y., Torralba, A., & Tenenbaum, J. B. (2022) · arXiv · doi:10.48550/arxiv.2206.01714 · Cited by 295
Compositional Visual Generation with Composable Diffusion Models
Liu, N., Li, S., Du, Y., Torralba, A., & Tenenbaum, J. B. (2022) · Lecture Notes in Computer Science · doi:10.1007/978-3-031-19790-1_26 · Cited by 282
Safe Latent Diffusion: Mitigating Inappropriate Degeneration in Diffusion Models
Schramowski, P., Brack, M., Deiseroth, B., & Kersting, K. (2023) · 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52729.2023.02157 · Cited by 219
Metadata
- Authors
- Parmar, G., Zhang, R., & Zhu, J.-Y.
- Venue
- 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- Publisher
- IEEE
- Published
- 2022-06
- Pages
- 11400-11410
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W4312694728
- Cited by
- 285
- References
- 64
- FWCI
- 23.85
- Type
- conference paper
- Language
- en
- Open access
- green
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.