DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | 이주호 | - |
dc.contributor.author | Keum, Seongho | - |
dc.contributor.author | 금성호 | - |
dc.date.accessioned | 2024-07-30T19:30:39Z | - |
dc.date.available | 2024-07-30T19:30:39Z | - |
dc.date.issued | 2024 | - |
dc.identifier.uri | http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=1096064&flag=dissertation | en_US |
dc.identifier.uri | http://hdl.handle.net/10203/321359 | - |
dc.description | 학위논문(석사) - 한국과학기술원 : 김재철AI대학원, 2024.2,[ii, 21 p. :] | - |
dc.description.abstract | Whole slide image (WSI) classification requires repetitive zoom-in and out for pathologists, as only small portions of the slide may be relevant to detecting cancer. Due to the lack of patch-level labels, multiple instance learning (MIL) is a common practice for training a WSI classifier. One of the challenges in MIL for WSIs is the weak supervision coming only from the slide-level labels, often resulting in severe overfitting. In response, researchers have considered adopting patch-level augmentation or applying mixup augmentation, but their applicability remains unverified. Our approach augments the training dataset by sampling a subset of patches in the WSI without significantly altering the underlying semantics of the original slides. Additionally, we introduce an efficient model (Slot-MIL) that organizes patches into a fixed number of slots, the abstract representation of patches, using an attention mechanism. We empirically demonstrate that the subsampling augmentation helps to make more informative slots by restricting the over-concentration of attention and to improve interpretability. Finally, we illustrate that combining our attention-based aggregation model with subsampling and mixup, which has shown limited compatibility in existing MIL methods, can enhance both generalization and calibration. Our proposed methods achieve the state-of-the-art performance across various benchmark datasets including class imbalance and distribution shifts. | - |
dc.language | eng | - |
dc.publisher | 한국과학기술원 | - |
dc.subject | 다중 인스턴스 학습▼a어텐션 방법론▼a조직 병리학▼a약한 지도학습 | - |
dc.subject | Multiple instance learning▼aAttention mechanism▼aHistopathology▼aWeakly-supervised learning | - |
dc.title | Slot-mixup with subsampling: a simple regularization for WSI classification | - |
dc.title.alternative | 서브샘플링에 기반한 슬롯-믹스업: 전체 슬라이드 이미지 분류를 위한 간단한 정규화 | - |
dc.type | Thesis(Master) | - |
dc.identifier.CNRN | 325007 | - |
dc.description.department | 한국과학기술원 :김재철AI대학원, | - |
dc.contributor.alternativeauthor | Lee, Juho | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.