ADFA: ATTENTION-AUGMENTED DIFFERENTIABLE TOP-K FEATURE ADAPTATION FOR UNSUPERVISED MEDICAL ANOMALY DETECTION | |
Yiming Huang1,2; Guole Liu1,2; Yaoru Luo1,2; Ge Yang1,2 | |
2023 | |
会议日期 | October 8 to October 11, 2023 |
会议地点 | Kuala Lumpur |
英文摘要 | The scarcity of annotated data, particularly for rare diseases, limits the variability of training data and the range of de- tectable lesions, presenting a significant challenge for super- vised anomaly detection in medical imaging. To solve this problem, we propose a novel unsupervised method for med- ical image anomaly detection: Attention-Augmented Differ- entiable top-k Feature Adaptation (ADFA). The method uti- lizes Wide-ResNet50-2 (WR50) network pre-trained on Ima- geNet to extract initial feature representations. To reduce the channel dimensionality while preserving relevant channel in- formation, we employ an attention-augmented patch descrip- tor on the extracted features. We then apply differentiable top- k feature adaptation to train the patch descriptor, mapping the extracted feature representations to a new vector space, en- abling effective detection of anomalies. Experiments show that ADFA outperforms state-of-the-art (SOTA) methods on multiple challenging medical image datasets, confirming its effectiveness in medical anomaly detection. |
内容类型 | 会议论文 |
源URL | [http://ir.ia.ac.cn/handle/173211/57365] ![]() |
专题 | 模式识别国家重点实验室_计算生物学与机器智能 |
通讯作者 | Ge Yang |
作者单位 | 1.School of Artificial Intelligence, University of Chinese Academy of Sciences 2.State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences |
推荐引用方式 GB/T 7714 | Yiming Huang,Guole Liu,Yaoru Luo,et al. ADFA: ATTENTION-AUGMENTED DIFFERENTIABLE TOP-K FEATURE ADAPTATION FOR UNSUPERVISED MEDICAL ANOMALY DETECTION[C]. 见:. Kuala Lumpur. October 8 to October 11, 2023. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论