Knowledge Commons of Institute of Automation,CAS
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 | |
会议名称 | 2023 IEEE International Conference on Image Processing (ICIP 2023) |
会议日期 | October 8 to October 11, 2023 |
会议地点 | Kuala Lumpur |
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. |
收录类别 | EI |
七大方向——子方向分类 | 计算智能 |
国重实验室规划方向分类 | AI For Science |
是否有论文关联数据集需要存交 | 否 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/57365 |
专题 | 多模态人工智能系统全国重点实验室_计算生物学与机器智能 |
通讯作者 | Ge Yang |
作者单位 | 1.State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences 2.School of Artificial Intelligence, University of Chinese Academy of Sciences |
第一作者单位 | 中国科学院自动化研究所 |
通讯作者单位 | 中国科学院自动化研究所 |
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],2023. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
【ICIP 2023】 Adfa-Att(1487KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
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