CoChat
Sign Up
Cited by 1Image and Video Quality AssessmentImage Retrieval and Classification TechniquesDigital Media Forensic Detection

Alignment of Perceptual Similarity Metrics with Human Perception

Open access
Ghildyal, Abhijay·2025
DOI 10.15760/etd.4012
Open this paper in CoChat — free accountOpen PDF

Abstract

Perceptual similarity metrics are used for quantitatively evaluating the similarity between two images as it would appear to human perception. These metrics aim to mimic the human visual system, providing a more accurate assessment of visual similarity. Such visual assessments are considered to be more advanced than simple pixel-wise comparisons such as ℓp norm distances. Thus, a human-like assessment of visual similarity, makes the metrics valuable for applications in image compression, restoration, and enhancement, where evaluating perceptual quality is crucial. Perceptual similarity metrics have progressively become more correlated with human judgments on perceptual similarity; however, despite recent advances, the addition of an imperceptible distortion can still compromise these metrics. This dissertation investigates how the magnitude of specific perturbations applied to visual stimuli affects the responses of low-level perceptual similarity metrics, with the goal of determining how imperceptible distortions impact the reliability of these metrics. We begin by investigating the robustness of perceptual similarity metrics against an imperceptible geometrical distortion that can occasionally occur during image acquisition and preprocessing. Existing perceptual similarity metrics assume an image and its reference are well aligned. As a result, these metrics are often sensitive to a small alignment error that is imperceptible to the human eyes. In this dissertation, we first study the effect of small misalignment, specifically a small shift between the input and reference image, on existing metrics, and accordingly develops a shift-tolerant similarity metric. We build upon LPIPS, a widely used learned perceptual similarity metric, and explores architectural design considerations to make it robust against imperceptible misalignment. Specifically, we study a wide spectrum of neural network elements, such as anti-aliasing filtering, pooling, striding, padding, and skip connection, and discuss their roles in making a robust metric. Based on our studies, we develop a new deep neural network-based perceptual similarity metric. Our experiments show that our metric is tolerant to imperceptible shifts while being consistent with the human similarity judgment. We further extend our investigation by systematically evaluating the robustness of these metrics to imperceptible adversarial perturbations. We call these perturbations adversarial, as they are deliberately crafted by an attacker with malicious intent. Following the two-alternative forced-choice experimental design with two distorted images and one reference image, we perturb the distorted image closer to the reference via an adversarial attack until the metric flips its judgment. We first show that all metrics in our study are susceptible to perturbations generated via common adversarial

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.15760/etd.4012

Cites

Statistics

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • Feature-based similarity methods are robust to illumination changes and affine transformations.

    “Feature-Based Similarity [23-28]: By extracting high-level primitives such as edges, corners, and shapes using algorithms like ORB (Oriented FAST and Rotated BRIEF), these methods are robust to illumination changes and affine transformations.”

    From A Survey and Tutorial on Image Quality Assessment with a Contrast-Weighted Structural Similarity Framework (2026) · cites this paper as [27]

    Section 2.3, “Geometric Robustness” (page unavailable), reports that a feature-embedding metric, DISTS, is robust to local and global distortions. That supports a narrower claim about some feature-based metrics, but our copy does not establish robustness to illumination changes or affine transformations, or discuss ORB as the cited sentence does. (LLM, conf=0.79)

    Experimental — accuracy not yet measured

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Cites

No references could be resolved yet.

Research works printed but not linked: 114

  1. Anish Athalye, Nicholas Carlini, and David Wagner. Obfuscated gradients give a false sense of security: Circumventing defenses to adversarial examples. In International Conference on Machine Learning, volume 80, pages 274-283, 2018.
  2. Aharon Azulay and Yair Weiss. Why do deep convolutional networks gener- alize so poorly to small image transformations? Journal of Machine Learning Research, 20(184):1-25, 2019.
  3. Sangnie Bhardwaj, Ian Fischer, Johannes Ballé, and Troy Chinen. An unsu- pervised information-theoretic perceptual quality metric. Advances in Neural Information Processing Systems, 33:13-24, 2020.
  4. Anand Bhattad, Min Jin Chong, Kaizhao Liang, Bo Li, and DA Forsyth. Un- restricted adversarial examples via semantic manipulation. In International Conference on Learning Representations, 2019.
  5. Sebastian Bosse, Dominique Maniry, Klaus-Robert Müller, Thomas Wiegand, and Wojciech Samek. Deep neural networks for no-reference and full-reference image quality assessment. IEEE Transactions on Image Processing, 27(1):206- 219, 2018.
  6. Wieland Brendel, Jonas Rauber, and Matthias Bethge. Decision-based adver- sarial attacks: Reliable attacks against black-box machine learning models. In International Conference on Learning Representations, 2018.
  7. Nicholas Carlini and David Wagner. Towards evaluating the robustness of neu- ral networks. In IEEE Symposium on Security and Privacy, pages 39-57, 2017.
  8. Mathilde Caron, Hugo Touvron, Ishan Misra, et al. Emerging properties in self-supervised vision transformers. In International Conference on Computer Vision, pages 9650-9660, 2021.
  9. CLIC. Workshop and challenge on learned image compression. http://www. compression.cc/, 2022.
  10. Francesco Croce, Maksym Andriushchenko, Vikash Sehwag, Edoardo Debenedetti, Nicolas Flammarion, Mung Chiang, Prateek Mittal, and Matthias Hein. Robustbench: a standardized adversarial robustness benchmark. arXiv/2010.09670, 2020.
  11. Francesco Croce, Christian Schlarmann, Naman Deep Singh, and Matthias Hein. Adversarially robust CLIP models induce better (robust) perceptual metrics. In ICML Wkshp. on Foundation Models in the Wild, 2024.
  12. Steffen Czolbe, Oswin Krause, Ingemar Cox, and Christian Igel. A loss function for generative neural networks based on watson's perceptual model. In Advances in Neural Information Processing Systems, volume 33, pages 2051-2061, 2020.
  13. Keyan Ding, Yi Liu, Xueyi Zou, Shiqi Wang, and Kede Ma. Locally adaptive structure and texture similarity for image quality assessment. In Proceedings of the 29th ACM International Conference on Multimedia, pages 2483-2491, 2021.
  14. Keyan Ding, Kede Ma, Shiqi Wang, and Eero P. Simoncelli. Image quality assessment: Unifying structure and texture similarity. IEEE Transactions on Pattern Analysis and Machine Intelligence, pages 1-1, 2020.
  15. Hadi Mohaghegh Dolatabadi, Sarah Erfani, and Christopher Leckie. Advflow: Inconspicuous black-box adversarial attacks using normalizing flows. In Ad- vances in Neural Information Processing Systems, 2020.
  16. Yinpeng Dong, Fangzhou Liao, Tianyu Pang, Hang Su, Jun Zhu, Xiaolin Hu, and Jianguo Li. Boosting adversarial attacks with momentum. In IEEE Con- ference on Computer Vision and Pattern Recognition, pages 9185-9193, 2018.
  17. Alexey Dosovitskiy, Lucas Beyer, A Kolesnikov, et al. An image is worth 16x16 words: Transformers for image recognition at scale. International Conference on Learning Representations, 2021.
  18. Alexey Dosovitskiy and Thomas Brox. Generating images with perceptual sim- ilarity metrics based on deep networks. In Advances in Neural Information Processing Systems, pages 658-666, 2016.
  19. Logan Engstrom, Brandon Tran, Dimitris Tsipras, Ludwig Schmidt, and Alek- sander Madry. Exploring the landscape of spatial robustness. In International Conference on Machine Learning, pages 1802-1811, 2019.
  20. Mark Everingham, Luc Van Gool, Christopher KI Williams, John Winn, and Andrew Zisserman. The PASCAL Visual Object Classes Challenge 2007 (VOC2007) Results. International Journal of Computer Vision, 88(2):303-338, 2010.
  21. Stephanie Fu, Netanel Tamir, Shobhita Sundaram, et al. Dreamsim: Learning new dimensions of human visual similarity using synthetic data. Advances in Neural Information Processing Systems, 36, 2024.
  22. Sara Ghazanfari, Siddharth Garg, Prashanth Krishnamurthy, Farshad Khor- rami, and Alexandre Araujo. R-LPIPS: An adversarially robust perceptual similarity metric. In ICML Wkshp. on New Frontiers in Adversarial Machine Learning, 2023.
  23. Abhijay Ghildyal, Nabajeet Barman, and Saman Zadtootaghaj. Foundation models boost low-level perceptual similarity metrics. In ICASSP 2025-2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pages 1-5. IEEE, 2025.
  24. Abhijay Ghildyal and Feng Liu. Shift-tolerant perceptual similarity metric. In European Conference on Computer Vision, pages 91-107, 2022.
  25. Ian Goodfellow, Jonathon Shlens, and Christian Szegedy. Explaining and har- nessing adversarial examples. In International Conference on Learning Repre- sentations, 2015.
  26. J Gu, H Cai, H Chen, X Ye, J Ren, and C Dong. Pipal: a large-scale im- age quality assessment dataset for perceptual image restoration. In European Conference on Computer Vision, pages 633-651, 2020.
  27. Jinjin Gu, Haoming Cai, Haoyu Chen, Xiaoxing Ye, Jimmy S. Ren, and Chao Dong. Pipal: A large-scale image quality assessment dataset for perceptual image restoration. In European Conference on Computer Vision, volume 12356, pages 633-651, 2020.
  28. Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. Deep residual learning for image recognition. In IEEE Conference on Computer Vision and Pattern Recognition, pages 770-778, 2016.
  29. Selig Hecht. The visual discrimination of intensity and the weber-fechner law. The Journal of general physiology, 7(2):235, 1924.
  30. Olivier J Hénaff and Eero P Simoncelli. Geodesics of learned representations. In International Conference on Learning Representations, 2016.
  31. Pablo Hernández-Cámara, Jorge Vila-Tomás, Jesus Malo, and Valero Laparra. Measuring human-CLIP alignment at different abstraction levels. In ICLR Wkshp. on Representational Alignment, 2024.
  32. Sanghyun Hong, Yigitcan Kaya, Ionut , -Vlad Modoranu, and Tudor Dumitras. A panda? no, it's a sloth: Slowdown attacks on adaptive multi-exit neural network inference. In International Conference on Learning Representations, 2021.
  33. Hossein Hosseini and Radha Poovendran. Semantic adversarial examples. In IEEE Conference on Computer Vision and Pattern Recognition Workshops, pages 1614-1619, 2018.
  34. Qian Huang, Isay Katsman, Horace He, Zeqi Gu, Serge Belongie, and Ser-Nam Lim. Enhancing adversarial example transferability with an intermediate level attack. In IEEE International Conference on Computer Vision, pages 4733- 4742, 2019.
  35. Forrest N. Iandola, Song Han, Matthew W. Moskewicz, Khalid Ashraf, William J. Dally, and Kurt Keutzer. Squeezenet: Alexnet-level accuracy with 50x fewer parameters and <0.5mb model size. arXiv/1602.07360, 2016.
  36. Nathan Inkawhich, Wei Wen, Hai Helen Li, and Yiran Chen. Feature space perturbations yield more transferable adversarial examples. In IEEE Conference on Computer Vision and Pattern Recognition, pages 7066-7074, 2019.
  37. Md Amirul Islam, Sen Jia, and Neil D. B. Bruce. How much position informa- tion do convolutional neural networks encode? In International Conference on Learning Representations, 2020.
  38. Max Jaderberg, Karen Simonyan, Andrew Zisserman, et al. Spatial transformer networks. In Advances in neural information processing systems, volume 28, pages 2017-2025, 2015.
  39. Justin Johnson, Alexandre Alahi, and Li Fei-Fei. Perceptual losses for real- time style transfer and super-resolution. In European Conference on Computer Vision, volume 9906, pages 694-711, 2016.
  40. Tero Karras, Samuli Laine, Miika Aittala, Janne Hellsten, Jaakko Lehtinen, and Timo Aila. Analyzing and improving the image quality of stylegan. In IEEE Conference on Computer Vision and Pattern Recognition, pages 8110- 8119, 2020.
  41. Osman Semih Kayhan and Jan C. van Gemert. On translation invariance in cnns: Convolutional layers can exploit absolute spatial location. In IEEE Con- ference on Computer Vision and Pattern Recognition, pages 14262-14273, 2020.
  42. Markus Kettunen, Erik Härkönen, and Jaakko Lehtinen. Deep convolutional reconstruction for gradient-domain rendering. ACM Transactions on Graphics, 38, 2019.
  43. Markus Kettunen, Erik Härkönen, and Jaakko Lehtinen. E-lpips: Ro- bust perceptual image similarity via random transformation ensembles. arXiv/1906.03973, 2019.
  44. Alex Krizhevsky, Ilya Sutskever, and Geoffrey E Hinton. Imagenet classifica- tion with deep convolutional neural networks. Advances in neural information processing systems, 25, 2012.
  45. Alex Krizhevsky, Ilya Sutskever, and Geoffrey E. Hinton. ImageNet classifica- tion with deep convolutional neural networks. In Advances in Neural Informa- tion Processing Systems, pages 1106-1114, 2012.
  46. Manoj Kumar, Neil Houlsby, Nal Kalchbrenner, and Ekin Dogus Cubuk. Do better imagenet classifiers assess perceptual similarity better? Transactions on Machine Learning Research, 2022.
  47. Alexey Kurakin, Ian Goodfellow, and Samy Bengio. Adversarial examples in the physical world. International Conference on Learning Representations - Workshop, 2017.
  48. Cassidy Laidlaw and Soheil Feizi. Functional adversarial attacks. In Advances in Neural Information Processing Systems, 2019.
  49. Cassidy Laidlaw, Sahil Singla, and Soheil Feizi. Perceptual adversarial robust- ness: Defense against unseen threat models. In International Conference on Learning Representations, 2020.
  50. Christian Ledig, Lucas Theis, Ferenc Huszar, Jose Caballero, Andrew P. Aitken, Alykhan Tejani, Johannes Totz, Zehan Wang, and Wenzhe Shi. Photo- realistic single image super-resolution using a generative adversarial network. arXiv/1609.04802, 2016.
  51. Jake Lee, Junfeng Yang, and Zhangyang Wang. What does cnn shift invariance look like? a visualization study. In European Conference on Computer Vision -Workshops, pages 196-210, 2020.
  52. Qizhang Li, Yiwen Guo, and Hao Chen. Yet another intermediate-level attack. In European Conference on Computer Vision, pages 241-257, 2020.
  53. X Liao, X Wei, M Zhou, Z Li, and S Kwong. Image quality assessment: Mea- suring perceptual degradation via distribution measures in deep feature spaces. IEEE Transactions on Image Processing, 33:4044-4059, 2024.
  54. Justin D Lieber, Gerick M Lee, Najib J Majaj, and J Anthony Movshon. Sensi- tivity to naturalistic texture relies primarily on high spatial frequencies. Journal of vision, 23(2):4-4, 2023.
  55. Hanhe Lin, Vlad Hosu, and Dietmar Saupe. Kadid-10k: A large-scale artifi- cially distorted iqa database. In Tenth International Conference on Quality of Multimedia Experience (QoMEX), pages 1-3, 2019.
  56. Tsung-Yi Lin, Michael Maire, Serge Belongie, James Hays, Pietro Perona, Deva Ramanan, Piotr Dollár, and C Lawrence Zitnick. Microsoft coco: Common objects in context. In European conference on computer vision, pages 740-755. Springer, 2014.
  57. Dong C Liu and Jorge Nocedal. On the limited memory bfgs method for large scale optimization. Mathematical programming, 45(1):503-528, 1989.
  58. Jianzhao Liu, Xin Li, Yanding Peng, Tao Yu, and Zhibo Chen. Swiniqa: Learned swin distance for compressed image quality assessment. In IEEE Con- ference on Computer Vision and Pattern Recognition Workshops, pages 1795- 1799, 2022.
  59. Yanpei Liu, Xinyun Chen, Chang Liu, and Dawn Song. Delving into transferable adversarial examples and black-box attacks. In International Conference on Learning Representations, 2017.
  60. Ze Liu, Yutong Lin, Yue Cao, Han Hu, Yixuan Wei, Zheng Zhang, Stephen Lin, and Baining Guo. Swin transformer: Hierarchical vision transformer using shifted windows. In IEEE International Conference on Computer Vision, pages 10012-10022, 2021.
  61. Ning Lu, Li Dong, Diqun Yan, and Xianliang Jiang. On attacking deep image quality evaluator via spatial transform. In IEEE International Conference on Systems, Man, and Cybernetics, pages 2876-2881, 2022.
  62. Kede Ma, Zhengfang Duanmu, and Zhou Wang. Geometric transformation invariant image quality assessment using convolutional neural networks. In 2018 IEEE International Conference on Acoustics, Speech and Signal Processing, pages 6732-6736, 2018.
  63. Aleksander Madry, Aleksandar Makelov, Ludwig Schmidt, Dimitris Tsipras, and Adrian Vladu. Towards deep learning models resistant to adversarial at- tacks. In International Conference on Learning Representations, 2018.
  64. Saeed Mahloujifar, Chong Xiang, Vikash Sehwag, Sihui Dai, and Prateek Mit- tal. Robustness from perception. In International Conference on Learning Rep- resentations Workshop on Security and Safety in Machine Learning Systems, 2020.
  65. Chengzhi Mao, Scott Geng, Junfeng Yang, Xin Wang, and Carl Vondrick. Un- derstanding zero-shot adversarial robustness for large-scale models. In The Eleventh International Conference on Learning Representations.
  66. Douglas L Medin, Robert L Goldstone, and Dedre Gentner. Respects for simi- larity. Psychological review, 100(2):254, 1993.
  67. Aliaksei Mikhailiuk, María Pérez-Ortiz, and Rafal Mantiuk. Psychometric scal- ing of tid2013 dataset. In 2018 Tenth International Conference on Quality of Multimedia Experience (QoMEX), pages 1-6. IEEE, 2018.
  68. Vinod Nair and Geoffrey E Hinton. Rectified linear units improve restricted boltzmann machines. In International Conference on Machine Learning, pages 807-814, 2010.
  69. Simon Niklaus and Feng Liu. Softmax splatting for video frame interpolation. In IEEE Conference on Computer Vision and Pattern Recognition, pages 5437- 5446, 2020.
  70. Simon Niklaus, Long Mai, and Feng Liu. Video frame interpolation via adaptive separable convolution. In IEEE International Conference on Computer Vision, pages 261-270, 2017.
  71. Aude Oliva and Antonio Torralba. The role of context in object recognition. Trends in cognitive sciences, 11(12):520-527, 2007.
  72. M Oquab, T Darcet, T Moutakanni, et al. DINOv2: Learning robust visual fea- tures without supervision. Transactions on Machine Learning Research, 2024.
  73. Nicolas Papernot, P. Mcdaniel, I. Goodfellow, S. Jha, Z. B. Celik, and A. Swami. Practical black-box attacks against deep learning systems using adversarial ex- amples. arXiv/1602.02697, 2016.
  74. Luiz Pessoa and Ralph Adolphs. Emotion processing and the amygdala: from a'low road'to'many roads' of evaluating biological significance. Nature Reviews Neuroscience, 11(11):773-782, 2010.
  75. Ekta Prashnani, Hong Cai, Yasamin Mostofi, and Pradeep Sen. Pieapp: Percep- tual image-error assessment through pairwise preference. In IEEE Conference on Computer Vision and Pattern Recognition, pages 1808-1817, 2018.
  76. Alec Radford, Jong Wook Kim, Chris Hallacy, et al. Learning transferable visual models from natural language supervision. In International conference on machine learning, pages 8748-8763, 2021.
  77. Olga Russakovsky, Jia Deng, Hao Su, et al. Imagenet large scale visual recog- nition challenge. International journal of computer vision, 115:211-252, 2015.
  78. Mehdi S. M. Sajjadi, Bernhard Schölkopf, and Michael Hirsch. En- hanceNet: Single image super-resolution through automated texture synthesis. arXiv/1612.07919, 2016.
  79. Mehdi SM Sajjadi, Bernhard Scholkopf, and Michael Hirsch. Enhancenet: Sin- gle image super-resolution through automated texture synthesis. In IEEE In- ternational Conference on Computer Vision, pages 4491-4500, 2017.
  80. Ali Shahin Shamsabadi, Ricardo Sanchez-Matilla, and Andrea Cavallaro. Col- orfool: Semantic adversarial colorization. In IEEE Conference on Computer Vision and Pattern Recognition, pages 1151-1160, 2020.
  81. Karen Simonyan and Andrew Zisserman. Very deep convolutional networks for large-scale image recognition. In International Conference on Learning Repre- sentations, 2015.
  82. Sanghyun Son, Jaerin Lee, Seungjun Nah, Radu Timofte, Kyoung Mu Lee, Yi- hao Liu, Liangbin Xie, Li Siyao, Wenxiu Sun, Yu Qiao, Chao Dong, Woonsung Park, Wonyong Seo, Munchurl Kim, Wenhao Zhang, Pablo Navarrete Michelini, Kazutoshi Akita, and Norimichi Ukita. AIM 2020 challenge on video temporal super-resolution. In European Conference on Computer Vision -Workshops, pages 23-40, 2020.
  83. Yang Song, Rui Shu, Nate Kushman, and Stefano Ermon. Constructing un- restricted adversarial examples with generative models. Advances in Neural Information Processing Systems, 31, 2018.
  84. Rainer Storn and Kenneth Price. Differential evolution-a simple and efficient heuristic for global optimization over continuous spaces. Journal of global opti- mization, 11(4):341-359, 1997.
  85. Jiawei Su, Danilo Vasconcellos Vargas, and Kouichi Sakurai. One pixel attack for fooling deep neural networks. IEEE Transactions on Evolutionary Compu- tation, 23(5):828-841, 2019.
  86. Christian Szegedy, Wojciech Zaremba, Ilya Sutskever, Joan Bruna, Dumitru Er- han, Ian Goodfellow, and Rob Fergus. Intriguing properties of neural networks. International Conference on Learning Representations, 2014.
  87. Hossein Talebi and Peyman Milanfar. Nima: Neural image assessment. IEEE Transactions on Image Processing, 27(8):3998-4011, 2018.
  88. Mingxing Tan and Quoc Le. EfficientNet: Rethinking model scaling for con- volutional neural networks. In International Conference on Machine Learning, volume 97, pages 6105-6114, 2019.
  89. Florian Tramèr, Nicholas Carlini, Wieland Brendel, and Aleksander Madry. On adaptive attacks to adversarial example defenses. Advances in Neural Informa- tion Processing Systems, 33, 2020.
  90. Florian Tramèr, Nicolas Papernot, Ian Goodfellow, Dan Boneh, and Patrick McDaniel. The space of transferable adversarial examples. arXiv/1704.03453, 2017.
  91. Amos Tversky. Features of similarity. Psychological review, 84(4):327, 1977.
  92. Jonathan Vacher and Pascal Mamassian. Perceptual scales predicted by fisher information metrics. In International Conference on Learning Representations, 2024.
  93. Cristina Vasconcelos, Hugo Larochelle, Vincent Dumoulin, Rob Romijnders, Nicolas Le Roux, and Ross Goroshin. Impact of aliasing on generalization in deep convolutional networks. In IEEE International Conference on Computer Vision, 2021.
  94. Jianyi Wang, Kelvin CK Chan, and Chen Change Loy. Exploring clip for assess- ing the look and feel of images. In AAAI Conference on Artificial Intelligence, volume 37, pages 2555-2563, 2023.
  95. Yajie Wang, Shangbo Wu, Wenyi Jiang, Shengang Hao, Yu-an Tan, and Quanxin Zhang. Demiguise attack: Crafting invisible semantic adversarial per- turbations with perceptual similarity. In International Joint Conference on Artificial Intelligence, pages 3125-3133, 2021.
  96. Zhou Wang, Alan C Bovik, Hamid R Sheikh, and Eero P Simoncelli. Image quality assessment: from error visibility to structural similarity. IEEE transac- tions on Image Processing, 13(4):600-612, 2004.
  97. Zhou Wang and Eero P Simoncelli. Translation insensitive image similarity in complex wavelet domain. In IEEE International Conference on Acoustics, Speech, and Signal Processing, volume 2, pages ii-573, 2005.
  98. Zhou Wang, Eero P Simoncelli, and Alan C Bovik. Multiscale structural simi- larity for image quality assessment. In The Thrity-Seventh Asilomar Conference on Signals, Systems & Computers, volume 2, pages 1398-1402. IEEE, 2003.
  99. Andrew B Watson. DCT quantization matrices visually optimized for individual images. In Human vision, visual processing, and digital display IV, volume 1913, pages 202-216. International Society for Optics and Photonics, 1993.
  100. Eric Wong, Frank Schmidt, and Zico Kolter. Wasserstein adversarial examples via projected Sinkhorn iterations. In International Conference on Machine Learning, volume 97, pages 6808-6817, 2019.
  101. Lei Wu and Zhanxing Zhu. Towards understanding and improving the trans- ferability of adversarial examples in deep neural networks. In Asian Conference on Machine Learning, volume 129 of PMLR, pages 837-850, 18-20 Nov 2020.
  102. Chaowei Xiao, Jun-Yan Zhu, Bo Li, Warren He, Mingyan Liu, and Dawn Song. Spatially transformed adversarial examples. In International Conference on Learning Representations, 2018.
  103. Cihang Xie, Jianyu Wang, Zhishuai Zhang, Zhou Ren, and Alan Yuille. Miti- gating adversarial effects through randomization. In International Conference on Learning Representations, 2018.
  104. Cihang Xie, Zhishuai Zhang, Yuyin Zhou, Song Bai, Jianyu Wang, Zhou Ren, and Alan Yuille. Improving transferability of adversarial examples with input diversity. In IEEE Conference on Computer Vision and Pattern Recognition, pages 2725-2734, 2019.
  105. Xiaohui Zeng, Chenxi Liu, Yu-Siang Wang, Weichao Qiu, Lingxi Xie, Yu-Wing Tai, Chi-Keung Tang, and Alan L Yuille. Adversarial attacks beyond the image space. In IEEE Conference on Computer Vision and Pattern Recognition, 2019.
  106. Huan Zhang, Hongge Chen, Zhao Song, Duane Boning, Inderjit S Dhillon, and Cho-Jui Hsieh. The limitations of adversarial training and the blind-spot attack. In International Conference on Learning Representations, 2018.
  107. Kai Zhang, Shuhang Gu, and Radu Timofte. NTIRE 2020 challenge on percep- tual extreme super-resolution: Methods and results. In IEEE Conference on Computer Vision and Pattern Recognition Workshops, pages 492-493, 2020.
  108. Lin Zhang, Lei Zhang, Xuanqin Mou, and David Zhang. FSIM: a feature similar- ity index for image quality assessment. IEEE Transactions on Image Processing, 20(8):2378-2386, 2011.
  109. Richard Zhang. Making convolutional networks shift-invariant again. In Inter- national Conference on Machine Learning, pages 7324-7334, 2019.
  110. Richard Zhang, Phillip Isola, Alexei A Efros, Eli Shechtman, and Oliver Wang. The unreasonable effectiveness of deep features as a perceptual metric. In IEEE Conference on Computer Vision and Pattern Recognition, pages 586-595, 2018.
  111. Weixia Zhang, Dingquan Li, Xiongkuo Min, Guangtao Zhai, Guodong Guo, Xiaokang Yang, and Kede Ma. Perceptual attacks of no-reference image quality models with human-in-the-loop. In Advances in Neural Information Processing Systems, 2022.
  112. Wen Zhou, Xin Hou, Yongjun Chen, Mengyun Tang, Xiangqi Huang, Xiang Gan, and Yong Yang. Transferable adversarial perturbations. In European Conference on Computer Vision, pages 452-467, 2018.
  113. Jun-Yan Zhu, Philipp Krähenbühl, Eli Shechtman, and Alexei A. Efros. Genera- tive visual manipulation on the natural image manifold. In European Conference on Computer Vision, volume 9909, pages 597-613, 2016.
  114. Xueyan Zou, Fanyi Xiao, Zhiding Yu, Yuheng Li, and Yong Jae Lee. Delving deeper into anti-aliasing in convnets. International Journal of Computer Vision, 131(1):67-81, 2023.

Cited by

Sorted by citations

Authors
Ghildyal, A.
Affiliations
Portland State University (US)
Corresponding author
Ghildyal, Abhijay
ORCID
Ghildyal, Abhijay
Publisher
Portland State University Library
Published
2025-07-22
DOI
10.15760/etd.4012
OpenAlex
W4414600584
Cited by
0
References
0
Type
dissertation
Language
en
Open access
Locations
PDXScholar (Portland State University) (submittedVersion)
Funders
Portland State University
Topics
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Image and Video Quality Assessment
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Image Retrieval and Classification Techniques
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Digital Media Forensic Detection
Keywords
image quality assessment, image misalignment, LPIPS, adversarial robustness, deep learning architectures, anti-aliasing filtering, skip connections, visual perception, two-alternative forced choice

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