HYCEDIS: HYbrid Confidence Engine for Deep Document Intelligence System
Not on the map. Why?
Abstract (arXiv)
Measuring the confidence of AI models is critical for safely deploying AI in real-world industrial systems. One important application of confidence measurement is information extraction from scanned documents. However, there exists no solution to provide reliable confidence score for current state-of-the-art deep-learning-based information extractors. In this paper, we propose a complete and novel architecture to measure confidence of current deep learning models in document information extraction task. Our architecture consists of a Multi-modal Conformal Predictor and a Variational Cluster-oriented Anomaly Detector, trained to faithfully estimate its confidence on its outputs without the need of host models modification. We evaluate our architecture on real-wold datasets, not only outperforming competing confidence estimators by a huge margin but also demonstrating generalization ability to out-of-distribution data.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 29 of its 41 references that are in the map. First posted on arXiv 1 Jun 2022.
Builds on
29 of 41 references.
References · 29
- 2017On Calibration of Modern Neural Networkscited by 4,960
- 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,795
- 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,448
- 2015FaceNet: A Unified Embedding for Face Recognition and Clusteringcited by 2,849
- 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,385
- 2019LayoutLM: Pre-training of Text and Layout for Document Image Understandingcited by 553
- 2015An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognitioncited by 520
- 2018GANomaly: Semi-Supervised Anomaly Detection via Adversarial Trainingcited by 409
- 2018Graph Convolutional Networks for Text Classificationcited by 345
- 2018Why ReLU networks yield high-confidence predictions far away from the training data and how to mitigate the problemcited by 323
- 2019Character Region Awareness for Text Detectioncited by 278
- 2021ICDAR2019 Competition on Scanned Receipt OCR and Information Extractioncited by 256
17 more
- 2016Lip Reading Sentences in the Wildcited by 228
- 2016TextBoxes: A Fast Text Detector with a Single Deep Neural Networkcited by 119
- 2017Multi-modal Factorized Bilinear Pooling with Co-Attention Learning for Visual Question Answeringcited by 117
- 2018TextSnake: A Flexible Representation for Detecting Text of Arbitrary Shapescited by 114
- 2017Learning to Extract Semantic Structure from Documents Using Multimodal Fully Convolutional Neural Networkcited by 92
- 2018Rotation-Sensitive Regression for Oriented Scene Text Detectioncited by 88
- 2019Graph Convolution for Multimodal Information Extraction from Visually Rich Documentscited by 88
- 2016Recursive Recurrent Nets with Attention Modeling for OCR in the Wildcited by 74
- 2018An end-to-end TextSpotter with Explicit Alignment and Attentioncited by 50
- 2018GraphIE: A Graph-Based Framework for Information Extractioncited by 45
- 2017Deep Matching Prior Network: Toward Tighter Multi-oriented Text Detectioncited by 31
- 2017Single Shot Text Detector with Regional Attentioncited by 31
- 2017Distance-based Confidence Score for Neural Network Classifierscited by 30
- 2018Dual Memory Neural Computer for Asynchronous Two-view Sequential Learningcited by 27
- 2018Confidence Prediction for Lexicon-Free OCRcited by 4
- 2021End-to-End Information Extraction by Character-Level Embedding and Multi-Stage Attentional U-Netcited by 4
- 2019Improving Long Handwritten Text Line Recognition with Convolutional Multi-way Associative Memorycited by 3
Built on by
Citing papers per year: 2025: 1; 2026: 1.
2 papers.