STR-Cert: Robustness Certification for Deep Text Recognition on Deep Learning Pipelines and Vision Transformers
원문 초록
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.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Linguistics-aware Masked Image Modeling for Self-supervised Scene Text Recognition
EventSTR: A Benchmark Dataset and Baselines for Event Stream based Scene Text Recognition
Ocean-OCR: Towards General OCR Application via a Vision-Language Model
TextSSR: Diffusion-based Data Synthesis for Scene Text Recognition
SVTRv2: CTC Beats Encoder-Decoder Models in Scene Text Recognition
Boosting Semi-Supervised Scene Text Recognition via Viewing and Summarizing
토론
이 논문과 연결된 포럼 글이 아직 없습니다.