PAGE: Domain-Incremental Adaptation with Past-Agnostic Generative Replay for Smart Healthcare

2024-03-13 · Chia-Hao Li, Niraj K. Jha

We propose PAGE, a domain-incremental adaptation strategy with past-agnostic generative replay for smart healthcare. PAGE enables generative replay without the aid of any preserved data or information from prior domains. When adapting to a new domain, it exploits real data from the new distribution and the current model to generate synthetic data that retain the learned knowledge of previous domains. By replaying the synthetic data with the new real data during training, PAGE achieves a good balance between domain adaptation and knowledge retention. In addition, we incorporate an extended inductive conformal prediction (EICP) method into PAGE to produce a confidence score and a credibility value for each detection result. This makes the predictions interpretable and provides statistical guarantees for disease detection in smart healthcare applications. We demonstrate PAGE's effectiveness in domain-incremental disease detection with three distinct disease datasets collected from commercially available WMSs. PAGE achieves highly competitive performance against state-of-the-art with superior scalability, data privacy, and feasibility. Furthermore, PAGE can enable up to 75% reduction in clinical workload with the help of EICP.

📄 PDF Abstract BibTeX arXiv:2403.08197

Code (0)

등록된 구현이 없습니다.

Tasks

Conformal PredictionDomain Adaptation

FRIDA -- Generative Feature Replay for Incremental Domain Adaptation

2021-12-28 · Sayan Rakshit, Anwesh Mohanty, Ruchika Chavhan, Biplab Banerjee 외

We tackle the novel problem of incremental unsupervised domain adaptation (IDA) in this paper. We assume that a labeled source domain and different unlabeled target domains are incrementally observed with the constraint …

Domain Adaptation Generative Adversarial Network Unsupervised Domain Adaptation

Adversarial Learning Networks: Source-free Unsupervised Domain Incremental Learning

2023-01-28 · Abhinit Kumar Ambastha, Leong Tze Yun

This work presents an approach for incrementally updating deep neural network (DNN) models in a non-stationary environment. DNN models are sensitive to changes in input data distribution, which limits their application t…

Continual Learning Disease Prediction Domain Adaptation Ensemble Learning+3

DA-CIL: Towards Domain Adaptive Class-Incremental 3D Object Detection

2022-12-05 · Ziyuan Zhao, Mingxi Xu, Peisheng Qian, Ramanpreet Singh Pahwa 외

Deep learning has achieved notable success in 3D object detection with the advent of large-scale point cloud datasets. However, severe performance degradation in the past trained classes, i.e., catastrophic forgetting, s…

3D Object Detection class-incremental learning Class Incremental Learning Class-Incremental Object Detection+5

Bidirectional Domain Mixup for Domain Adaptive Semantic Segmentation

2023-03-17 · Daehan Kim, Minseok Seo, KwanYong Park, Inkyu Shin 외

Mixup provides interpolated training samples and allows the model to obtain smoother decision boundaries for better generalization. The idea can be naturally applied to the domain adaptation task, where we can mix the so…

Domain Adaptation Pseudo Label Semantic Segmentation

Versatile Incremental Learning: Towards Class and Domain-Agnostic Incremental Learning

2024-09-17 · Min-Yeong Park, Jae-Ho Lee, Gyeong-Moon Park

Incremental Learning (IL) aims to accumulate knowledge from sequential input tasks while overcoming catastrophic forgetting. Existing IL methods typically assume that an incoming task has only increments of classes or do…

Incremental Learning