A MIL-based framework via contrastive instance learning and multimodal learning for long-term ECG classification

Haozhan Han, Cheng Lian, Bingrong Xu, Zhigang Zeng, Adi Alhudhaif, Kemal Polat

Abstract: Highlights•We propose a model CIMIL for long-term ECG classification.•We propose an instance interactor to improve the interaction among instances.•We propose a novel fusion method to enhance the performance of model.•We propose a contrastive instance loss to the model to distinguish instances.