DC Field | Value | Language |
---|---|---|
dc.contributor.author | 신범조 | - |
dc.date.accessioned | 2022-03-29T03:14:30Z | - |
dc.date.available | 2022-03-29T03:14:30Z | - |
dc.date.issued | 2021 | - |
dc.identifier.other | OAK-2015-08696 | - |
dc.identifier.uri | http://postech.dcollection.net/common/orgView/200000366650 | ko_KR |
dc.identifier.uri | https://oasis.postech.ac.kr/handle/2014.oak/111501 | - |
dc.description | Master | - |
dc.description.abstract | Multiple Instance Learning (MIL) involves predicting a single binary label for a bag of instances, given positive or negative labels at bag-level. Since a positive bag contains both positive and negative instances, it is often required to detect positive instances (key instances) when a set of instances is categorized as a positive bag. The attention-based deep MIL model is a recent advance in both bag-level classification and key instance detection (KID). However, if the positive and negative instances in a positive bag are not clearly distinguishable, the attention-based deep MIL model has limited KID performance as the attention scores are skewed to few positive instances. In this paper, we present a method to improve the attention-based deep MIL model in the task of KID. The main idea is to use the neural network inversion to find which instances made contribution to the bag-level prediction produced by the trained MIL model. Moreover, we apply L2 constraint in terms of data into the neural network inversion. Numerical experiments on an MNIST-based image MIL dataset and two real-world histopathology datasets verify the validity of our method, demonstrating the KID performance is significantly improved while the performance of bag-level prediction is maintained. | - |
dc.language | eng | - |
dc.publisher | 포항공과대학교 | - |
dc.title | Neural Network Inversion For Key Instance Detection In Multiple Instance Learning | - |
dc.title.alternative | 다중 인스턴스 학습에서 키 인스턴스 검출을 위한 뉴럴 네트워크 인버전 | - |
dc.type | Thesis | - |
dc.contributor.college | 일반대학원 컴퓨터공학과 | - |
dc.date.degree | 2021- 2 | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.
library@postech.ac.kr Tel: 054-279-2548
Copyrights © by 2017 Pohang University of Science ad Technology All right reserved.