DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | In So Kweon | - |
dc.contributor.advisor | 권인소 | - |
dc.contributor.author | Oh, Youngtaek | - |
dc.date.accessioned | 2022-04-21T19:32:32Z | - |
dc.date.available | 2022-04-21T19:32:32Z | - |
dc.date.issued | 2021 | - |
dc.identifier.uri | http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=948722&flag=dissertation | en_US |
dc.identifier.uri | http://hdl.handle.net/10203/295519 | - |
dc.description | 학위논문(석사) - 한국과학기술원 : 전기및전자공학부, 2021.2,[v, 32 p. :] | - |
dc.description.abstract | It is well known that label bias hinders the practical applications of deep learning approaches in the real-world. Since deep learning models optimally learn the biases existing in the dataset, they cannot generalize well to fair, real-world requirement. In real-world, especially in applications where safety and reliability are required, it is important to ensure that the model produces fair predictions even if the model is trained on a biased data. In this dissertation, we present a semi-supervised learning method that allows the model to be fair even in the training data where bias exists. When biased data is trained with typical semi-supervised learning methods, performances severely degrades, in some cases far less than that of the supervised learning counterpart. In this paper, we design a framework called Prototypical Semantic Alignment (PSA) to effectively prevent this problem. To this end, we propose 1) Online Clustering, an algorithm that clusters labeled data in an online-manner and 2) Semantic Alignment Loss which enforces the unlabeled images to be attracted to the most similar prototype obtained through clustering. As a result, we show significant performance gains by consuming additional unlabeled images in long-tailed distribution data and label-scarce scenarios, which are real examples of label bias. | - |
dc.language | eng | - |
dc.publisher | 한국과학기술원 | - |
dc.subject | Image classification▼aDataset bias▼aSemi-Supervised Learning▼aLong-tailed distribution▼aFew labels | - |
dc.subject | 이미지분류▼a데이터셋 편향▼a반지도학습▼a긴꼬리분포▼a극소라벨 | - |
dc.title | Robust semi-supervised learning to label bias | - |
dc.title.alternative | 레이블 편향에 강인한 반지도학습 방법 | - |
dc.type | Thesis(Master) | - |
dc.identifier.CNRN | 325007 | - |
dc.description.department | 한국과학기술원 :전기및전자공학부, | - |
dc.contributor.alternativeauthor | 오영택 | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.