ADFA: Attention-Augmented Differentiable Top-K Feature Adaptation for Unsupervised Medical Anomaly Detection

• Published in: 2023 IEEE International Conference on Image Processing (ICIP) pp. 206 - 210
• Main Authors: Huang, Yiming, Liu, Guole, Luo, Yaoru, Yang, Ge
• Format: Conference Proceeding
• Language: English
• Published: IEEE 08.10.2023
• Subjects: Anomaly detection; attention mechanism; Biomedical imaging; feature adaptation; Feature extraction; Image analysis; Lesions; Location awareness; medical image; Training data; unsupervised learning

The scarcity of annotated data, particularly for rare diseases, limits the variability of training data and the range of detectable lesions, presenting a significant challenge for supervised anomaly detection in medical imaging. To solve this problem, we propose a novel unsupervised method for medic...