paper-with-me

Papers

MINA: Multilevel Knowledge-Guided Attention for Modeling Electrocardiography Signals

2019-05-27 · Shenda Hong, Cao Xiao, Tengfei Ma, Hongyan Li, Jimeng Sun

Electrocardiography (ECG) signals are commonly used to diagnose various cardiac abnormalities. Recently, deep learning models showed initial success on modeling ECG data, however they are mostly black-box, thus lack interpretability needed for clinical usage. In this work, we propose MultIlevel kNowledge-guided Attention networks (MINA) that predict heart diseases from ECG signals with intuitive explanation aligned with medical knowledge. By extracting multilevel (beat-, rhythm- and frequency-level) domain knowledge features separately, MINA combines the medical knowledge and ECG data via a multilevel attention model, making the learned models highly interpretable. Our experiments showed MINA achieved PR-AUC 0.9436 (outperforming the best baseline by 5.51%) in real world ECG dataset. Finally, MINA also demonstrated robust performance and strong interpretability against signal distortion and noise contamination.

📄 PDF Abstract BibTeX arXiv:1905.11333

Code (1)

hsd1503/MINA 공식 구현 pytorch

Tasks

Electrocardiography (ECG)Rhythm

Methods 이 논문이 사용한 방법론

Interpretability 설명 없음

Similar Papers 제목 키워드 기반

M$^3$Net: Multilevel, Mixed and Multistage Attention Network for Salient Object Detection

2023-09-15 · Yao Yuan, Pan Gao, Xiaoyang Tan

Most existing salient object detection methods mostly use U-Net or feature pyramid structure, which simply aggregates feature maps of different scales, ignoring the uniqueness and interdependence of them and their respec…

object-detectionObject DetectionRGB Salient Object DetectionSalient Object Detection

Uncertainty Guided Refinement for Fine-Grained Salient Object Detection

2025-04-13 · Yao Yuan, Pan Gao, Qun Dai, Jie Qin 외

Recently, salient object detection (SOD) methods have achieved impressive performance. However, salient regions predicted by existing methods usually contain unsaturated regions and shadows, which limits the model for re…

object-detectionObject DetectionSaliency PredictionSalient Object Detection

Knowledge Guided Bidirectional Attention Network for Human-Object Interaction Detection

2022-07-16 · Jingjia Huang, Baixiang Yang

Human Object Interaction (HOI) detection is a challenging task that requires to distinguish the interaction between a human-object pair. Attention based relation parsing is a popular and effective strategy utilized in HO…

DecoderHuman-Object Interaction DetectionRelation

Longitudinal Deep Kernel Gaussian Process Regression

2020-05-24 · Junjie Liang, Yanting Wu, Dongkuan Xu, Vasant Honavar

Gaussian processes offer an attractive framework for predictive modeling from longitudinal data, i.e., irregularly sampled, sparse observations from a set of individuals over time. However, such methods have two key shor…

Gaussian ProcessesregressionVariational Inference

Extracting knowledge from features with multilevel abstraction

2021-12-04 · Jinhong Lin, Zhaoyang Li

Knowledge distillation aims at transferring the knowledge from a large teacher model to a small student model with great improvements of the performance of the student model. Therefore, the student network can replace th…

Data AugmentationKnowledge DistillationSelf-Knowledge Distillation