STR-Cert: Robustness Certification for Deep Text Recognition on Deep Learning Pipelines and Vision Transformers
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910294033301504 |
|---|---|
| author | Shao, Daqian Fesser, Lukas Kwiatkowska, Marta |
| author_facet | Shao, Daqian Fesser, Lukas Kwiatkowska, Marta |
| contents | Robustness certification, which aims to formally certify the predictions of neural networks against adversarial inputs, has become an integral part of important tool for safety-critical applications. Despite considerable progress, existing certification methods are limited to elementary architectures, such as convolutional networks, recurrent networks and recently Transformers, on benchmark datasets such as MNIST. In this paper, we focus on the robustness certification of scene text recognition (STR), which is a complex and extensively deployed image-based sequence prediction problem. We tackle three types of STR model architectures, including the standard STR pipelines and the Vision Transformer. We propose STR-Cert, the first certification method for STR models, by significantly extending the DeepPoly polyhedral verification framework via deriving novel polyhedral bounds and algorithms for key STR model components. Finally, we certify and compare STR models on six datasets, demonstrating the efficiency and scalability of robustness certification, particularly for the Vision Transformer. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_05338 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | STR-Cert: Robustness Certification for Deep Text Recognition on Deep Learning Pipelines and Vision Transformers Shao, Daqian Fesser, Lukas Kwiatkowska, Marta Computer Vision and Pattern Recognition Machine Learning Robustness certification, which aims to formally certify the predictions of neural networks against adversarial inputs, has become an integral part of important tool for safety-critical applications. Despite considerable progress, existing certification methods are limited to elementary architectures, such as convolutional networks, recurrent networks and recently Transformers, on benchmark datasets such as MNIST. In this paper, we focus on the robustness certification of scene text recognition (STR), which is a complex and extensively deployed image-based sequence prediction problem. We tackle three types of STR model architectures, including the standard STR pipelines and the Vision Transformer. We propose STR-Cert, the first certification method for STR models, by significantly extending the DeepPoly polyhedral verification framework via deriving novel polyhedral bounds and algorithms for key STR model components. Finally, we certify and compare STR models on six datasets, demonstrating the efficiency and scalability of robustness certification, particularly for the Vision Transformer. |
| title | STR-Cert: Robustness Certification for Deep Text Recognition on Deep Learning Pipelines and Vision Transformers |
| topic | Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2401.05338 |