Are Deep Models Robust against Real Distortions? A Case Study on Document Image Classification-Reference-Cited by-同舟云学术

Are Deep Models Robust against Real Distortions? A Case Study on Document Image Classification

Published:2022-08-21 Issue: Volume: Page:
ISSN:
Container-title:2022 26th International Conference on Pattern Recognition (ICPR)
language:
Short-container-title:

Author:

Saifullah ¹,Siddiqui Shoaib Ahmed¹,Agne Stefan¹,Dengel Andreas¹,Ahmed Sheraz¹

Affiliation:

1. German Research Center for Artificial Intelligence (DFKI),Kaiserslautern,Germany,67663

Publisher

IEEE

Link

http://xplorestaging.ieee.org/ielx7/9956007/9955631/09956167.pdf?arnumber=9956167

Reference41 articles.

1. AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty;hendrycks,2019

2. Using pre-training can improve model robustness and uncertainty;hendrycks;36th Int Conf Mach Learn ICML 2019,2019

3. Explaining and harnessing adversarial examples;goodfellow;3rd Int Conf Learn Represent ICLR 2015 Conf Track Proc International Conference on Learning Representations ICLR,2015

4. One Pixel Attack for Fooling Deep Neural Networks

5. Analyzing the Potential of Zero-Shot Recognition for Document Image Classification

Cited by 8 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. DocXclassifier: towards a robust and interpretable deep neural network for document image classification;International Journal on Document Analysis and Recognition (IJDAR);2024-06-25

2. Towards privacy preserved document image classification: a comprehensive benchmark;International Journal on Document Analysis and Recognition (IJDAR);2024-06-18

3. Selection of image classifiers for noisy images through metalearning;Proceedings of the 2024 7th International Conference on Machine Vision and Applications;2024-03-12

4. The Reality of High Performing Deep Learning Models: A Case Study on Document Image Classification;IEEE Access;2024

5. Latent Diffusion for Guided Document Table Generation;Lecture Notes in Computer Science;2024