DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | Kim, Daeshik | - |
dc.contributor.advisor | 김대식 | - |
dc.contributor.author | Lim, Dongho | - |
dc.date.accessioned | 2022-04-27T19:30:51Z | - |
dc.date.available | 2022-04-27T19:30:51Z | - |
dc.date.issued | 2021 | - |
dc.identifier.uri | http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=948971&flag=dissertation | en_US |
dc.identifier.uri | http://hdl.handle.net/10203/295928 | - |
dc.description | 학위논문(석사) - 한국과학기술원 : 전기및전자공학부, 2021.2,[v, 24 p. :] | - |
dc.description.abstract | Autonomous vehicle accidents are occurring even up to a recent date due to abnormal behavior of nearby traffic-agents. Abnormal agents are identified by observing the ambiguous behavior of the agents before the actual abnormality. Therefore, to effectively prevent accidents, models should be trained with soft labels of ambiguous situations. However, existing anomaly datasets only contain hard labels, which can not imply the ambiguity of the actual scenarios. To fully utilize the small number of hard labeled ambiguous data, we propose a simple and effective semi-supervised approach, namely STADAS. Our STADAS exploits two regulatory signals from unlabeled data. One signal is the ambiguity soft label indicating the ambiguity of the unlabeled samples which is computed from the teacher model. With our novel Ambiguity loss, our model can properly understand and handle ambiguous situations. The other is the pseudo distance label which connotes information about the dynamics of a vehicle. We show that our method has impressive anomaly detection ability quantitatively and qualitatively. Quantitatively, ours outperforms other semi-supervised methods (e.g., pseudo label, mean-teacher) regarding ROC-AUC and F1 score. Moreover, ours has fewer false negatives than the supervised model. Qualitatively, ours can detect ambiguous situations that other methods could not properly detect. | - |
dc.language | eng | - |
dc.publisher | 한국과학기술원 | - |
dc.subject | Semi-Supervised learning▼aAnomaly Detection▼aDeep learning▼aComputer Vision▼aCNN | - |
dc.subject | 준 지도 학습▼a이상 감지▼a딥러닝▼a컴퓨터 비전▼a합성곱 신경망 | - |
dc.title | STADAS: semi-supervised traffic anomaly detection with ambiguous samples from real-world situations | - |
dc.title.alternative | 실제 상황에서의 모호한 샘플을 사용한 준 지도 학습 이상 차량 탐지 | - |
dc.type | Thesis(Master) | - |
dc.identifier.CNRN | 325007 | - |
dc.description.department | 한국과학기술원 :전기및전자공학부, | - |
dc.contributor.alternativeauthor | 임동호 | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.