CVPR 2021 Open Access Repository

Fair, Data-Efficient, and Trusted Computer Vision

Sample-Free White-Box Out-of-Distribution Detection for Deep Learning: Jean-Michel Begon,

Pierre Geurts; [pdf] [supp]
[bibtex]
@InProceedings{Begon_2021_CVPR, author = {Begon, Jean-Michel and Geurts, Pierre}, title = {Sample-Free White-Box Out-of-Distribution Detection for Deep Learning}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2021}, pages = {3290-3299} }
A Theoretical-Empirical Approach to Estimating Sample Complexity of DNNs: Devansh Bisla,

Apoorva Nandini Saridena,

Anna Choromanska; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Bisla_2021_CVPR, author = {Bisla, Devansh and Saridena, Apoorva Nandini and Choromanska, Anna}, title = {A Theoretical-Empirical Approach to Estimating Sample Complexity of DNNs}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2021}, pages = {3270-3280} }
MLCapsule: Guarded Offline Deployment of Machine Learning as a Service: Lucjan Hanzlik,

Yang Zhang,

Kathrin Grosse,

Ahmed Salem,

Maximilian Augustin,

Michael Backes,

Mario Fritz; [pdf] [arXiv]
[bibtex]
@InProceedings{Hanzlik_2021_CVPR, author = {Hanzlik, Lucjan and Zhang, Yang and Grosse, Kathrin and Salem, Ahmed and Augustin, Maximilian and Backes, Michael and Fritz, Mario}, title = {MLCapsule: Guarded Offline Deployment of Machine Learning as a Service}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2021}, pages = {3300-3309} }
X-MAN: Explaining Multiple Sources of Anomalies in Video: Stanislaw Szymanowicz,

James Charles,

Roberto Cipolla; [pdf] [supp]
[bibtex]
@InProceedings{Szymanowicz_2021_CVPR, author = {Szymanowicz, Stanislaw and Charles, James and Cipolla, Roberto}, title = {X-MAN: Explaining Multiple Sources of Anomalies in Video}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2021}, pages = {3224-3232} }
A Mathematical Analysis of Learning Loss for Active Learning in Regression: Megh Shukla,

Shuaib Ahmed; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Shukla_2021_CVPR, author = {Shukla, Megh and Ahmed, Shuaib}, title = {A Mathematical Analysis of Learning Loss for Active Learning in Regression}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2021}, pages = {3320-3328} }
InfoScrub: Towards Attribute Privacy by Targeted Obfuscation: Hui-Po Wang,

Tribhuvanesh Orekondy,

Mario Fritz; [pdf] [arXiv]
[bibtex]
@InProceedings{Wang_2021_CVPR, author = {Wang, Hui-Po and Orekondy, Tribhuvanesh and Fritz, Mario}, title = {InfoScrub: Towards Attribute Privacy by Targeted Obfuscation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2021}, pages = {3281-3289} }
Estimating (and Fixing) the Effect of Face Obfuscation in Video Recognition: Matteo Tomei,

Lorenzo Baraldi,

Simone Bronzin,

Rita Cucchiara; [pdf]
[bibtex]
@InProceedings{Tomei_2021_CVPR, author = {Tomei, Matteo and Baraldi, Lorenzo and Bronzin, Simone and Cucchiara, Rita}, title = {Estimating (and Fixing) the Effect of Face Obfuscation in Video Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2021}, pages = {3263-3269} }
Explainable Deep Classification Models for Domain Generalization: Andrea Zunino,

Sarah Adel Bargal,

Riccardo Volpi,

Mehrnoosh Sameki,

Jianming Zhang,

Stan Sclaroff,

Vittorio Murino,

Kate Saenko; [pdf] [arXiv]
[bibtex]
@InProceedings{Zunino_2021_CVPR, author = {Zunino, Andrea and Bargal, Sarah Adel and Volpi, Riccardo and Sameki, Mehrnoosh and Zhang, Jianming and Sclaroff, Stan and Murino, Vittorio and Saenko, Kate}, title = {Explainable Deep Classification Models for Domain Generalization}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2021}, pages = {3233-3242} }
A Watermarking-Based Framework for Protecting Deep Image Classifiers Against Adversarial Attacks: Chen Sun,

En-Hui Yang; [pdf]
[bibtex]
@InProceedings{Sun_2021_CVPR, author = {Sun, Chen and Yang, En-Hui}, title = {A Watermarking-Based Framework for Protecting Deep Image Classifiers Against Adversarial Attacks}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2021}, pages = {3329-3338} }
Towards Fair Federated Learning With Zero-Shot Data Augmentation: Weituo Hao,

Mostafa El-Khamy,

Jungwon Lee,

Jianyi Zhang,

Kevin J Liang,

Changyou Chen,

Lawrence Carin Duke; [pdf] [supp]
[bibtex]
@InProceedings{Hao_2021_CVPR, author = {Hao, Weituo and El-Khamy, Mostafa and Lee, Jungwon and Zhang, Jianyi and Liang, Kevin J and Chen, Changyou and Duke, Lawrence Carin}, title = {Towards Fair Federated Learning With Zero-Shot Data Augmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2021}, pages = {3310-3319} }
An Adversarial Approach for Explaining the Predictions of Deep Neural Networks: Arash Rahnama,

Andrew Tseng; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Rahnama_2021_CVPR, author = {Rahnama, Arash and Tseng, Andrew}, title = {An Adversarial Approach for Explaining the Predictions of Deep Neural Networks}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2021}, pages = {3253-3262} }
Renofeation: A Simple Transfer Learning Method for Improved Adversarial Robustness: Ting-Wu Chin,

Cha Zhang,

Diana Marculescu; [pdf] [arXiv]
[bibtex]
@InProceedings{Chin_2021_CVPR, author = {Chin, Ting-Wu and Zhang, Cha and Marculescu, Diana}, title = {Renofeation: A Simple Transfer Learning Method for Improved Adversarial Robustness}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2021}, pages = {3243-3252} }