Robust Generalization Against Photon-Limited Corruptions via Worst-Case Sharpness Minimization-Reference-Cited by-同舟云学术

Robust Generalization Against Photon-Limited Corruptions via Worst-Case Sharpness Minimization

Published:2023-06 Issue: Volume: Page:
ISSN:
Container-title:2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
language:
Short-container-title:

Author:

Huang Zhuo¹,Zhu Miaoxi²,Xia Xiaobo¹,Shen Li³,Yu Jun⁴,Gong Chen⁵,Han Bo⁶,Du Bo²,Liu Tongliang¹

Affiliation:

1. The University of Sydney,Sydney AI Centre

2. Institute of Artificial Intelligence, School of Computer Science,National Engineering Research Center for Multimedia Software

3. JD Explore Academy

4. University of Science and Technology of China,Department of Automation

5. School of Computer Science and Engineering, Nanjing University of Science and Technology,Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education

6. Hong Kong Baptist University,Department of Computer Science

Funder

STI 2030-Major

Australian Research Council

Natural Science Foundation of China

USTC-IAT Application Sci. & Tech. Achievement Cultivation Program

Sci. & Tech. Innovation Special Zone

NSF

Publisher

IEEE

Link

http://xplorestaging.ieee.org/ielx7/10203037/10203050/10203447.pdf?arnumber=10203447

Reference71 articles.

1. Fairness without demographics in repeated loss minimization;hashimoto;ICML,2018

2. Adversarial weight perturbation helps robust generalization;wu;NeurIPS,2020

3. Explaining and harnessing adversarial examples;goodfellow;ICLRE,2015

4. Mitigating neural network overconfidence with logit normalization;wei;ICML,2022

5. A baseline for detecting misclassified and out-of-distribution examples in neural networks;hendrycks;ICLRE,2017

Cited by 6 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. SAFER-STUDENT for Safe Deep Semi-Supervised Learning With Unseen-Class Unlabeled Data;IEEE Transactions on Knowledge and Data Engineering;2024-01

2. Sharpness-Aware Minimization for Out-of-Distribution Generalization;Communications in Computer and Information Science;2023-11-13

3. PADDLES: Phase-Amplitude Spectrum Disentangled Early Stopping for Learning with Noisy Labels;2023 IEEE/CVF International Conference on Computer Vision (ICCV);2023-10-01

4. Enhancing Fine-Tuning based Backdoor Defense with Sharpness-Aware Minimization;2023 IEEE/CVF International Conference on Computer Vision (ICCV);2023-10-01

5. Holistic Label Correction for Noisy Multi-Label Classification;2023 IEEE/CVF International Conference on Computer Vision (ICCV);2023-10-01