Generalizable Deep Learning Method for Suppressing Unseen and Multiple MRI Artifacts Using Meta-learning

2023-04-13 · Arun Palla, Sriprabha Ramanarayanan, Keerthi Ram, Mohanasankar Sivaprakasam

Magnetic Resonance (MR) images suffer from various types of artifacts due to motion, spatial resolution, and under-sampling. Conventional deep learning methods deal with removing a specific type of artifact, leading to separately trained models for each artifact type that lack the shared knowledge generalizable across artifacts. Moreover, training a model for each type and amount of artifact is a tedious process that consumes more training time and storage of models. On the other hand, the shared knowledge learned by jointly training the model on multiple artifacts might be inadequate to generalize under deviations in the types and amounts of artifacts. Model-agnostic meta-learning (MAML), a nested bi-level optimization framework is a promising technique to learn common knowledge across artifacts in the outer level of optimization, and artifact-specific restoration in the inner level. We propose curriculum-MAML (CMAML), a learning process that integrates MAML with curriculum learning to impart the knowledge of variable artifact complexity to adaptively learn restoration of multiple artifacts during training. Comparative studies against Stochastic Gradient Descent and MAML, using two cardiac datasets reveal that CMAML exhibits (i) better generalization with improved PSNR for 83% of unseen types and amounts of artifacts and improved SSIM in all cases, and (ii) better artifact suppression in 4 out of 5 cases of composite artifacts (scans with multiple artifacts).

📄 PDF Abstract BibTeX arXiv:2304.06378

Code (0)

등록된 구현이 없습니다.

Tasks

Meta-Learning SSIM

Methods 이 논문이 사용한 방법론

MAML 설명 없음

Mimic Embedding via Adaptive Aggregation: Learning Generalizable Person Re-identification

2021-12-16 · Boqiang Xu, Jian Liang, Lingxiao He, Zhenan Sun

Domain generalizable (DG) person re-identification (ReID) aims to test across unseen domains without access to the target domain data at training time, which is a realistic but challenging problem. In contrast to methods…

Generalizable Person Re-identification Mixture-of-Experts Person Re-Identification Unsupervised Domain Adaptation

Suppressing Forgery-Specific Shortcuts for Generalizable Deepfake Detection

2026-06-01 · Yihui Wang, Yonghui Yang, Jilong Liu, Fengbin Zhu 외 arxiv

Deepfake detection suffers from poor generalization across forgery methods, as existing models tend to rely on spurious method-specific shortcuts that fail to transfer to unseen manipulations. While recent approaches att…

DeepFake Detection

Metalearning generalizable dynamics from trajectories

2023-01-03 · Qiaofeng Li, Tianyi Wang, Vwani Roychowdhury, M. Khalid Jawed

We present the interpretable meta neural ordinary differential equation (iMODE) method to rapidly learn generalizable (i.e., not parameter-specific) dynamics from trajectories of multiple dynamical systems that vary in t…

Inductive Bias Meta-Learning

A Multi-directional Meta-Learning Framework for Class-Generalizable Anomaly Detection

2026-01-27 · Padmaksha Roy, Lamine Mili, Almuatazbellah Boker arxiv

In this paper, we address the problem of class-generalizable anomaly detection, where the objective is to develop a unified model by focusing our learning on the available normal data and a small amount of anomaly data i…

Anomaly Detection

MAML-en-LLM: Model Agnostic Meta-Training of LLMs for Improved In-Context Learning

2024-05-19 · Sanchit Sinha, Yuguang Yue, Victor Soto, Mayank Kulkarni 외

Adapting large language models (LLMs) to unseen tasks with in-context training samples without fine-tuning remains an important research problem. To learn a robust LLM that adapts well to unseen tasks, multiple meta-trai…

In-Context Learning