DC Field | Value | Language |
---|---|---|
dc.contributor.author | Park, Dongmin | ko |
dc.contributor.author | Shin, Yooju | ko |
dc.contributor.author | Bang, Jihwan | ko |
dc.contributor.author | Lee, Youngjun | ko |
dc.contributor.author | Song, Hwanjun | ko |
dc.contributor.author | Lee, Jae-Gil | ko |
dc.date.accessioned | 2023-02-01T07:02:05Z | - |
dc.date.available | 2023-02-01T07:02:05Z | - |
dc.date.created | 2023-01-03 | - |
dc.date.issued | 2022-12-01 | - |
dc.identifier.citation | 36th Conference on Neural Information Processing Systems, NeurIPS 2022 | - |
dc.identifier.uri | http://hdl.handle.net/10203/304927 | - |
dc.description.abstract | Unlabeled data examples awaiting annotations contain open-set noise inevitably. A few active learning studies have attempted to deal with this open-set noise for sample selection by filtering out the noisy examples. However, because focusing on the purity of examples in a query set leads to overlooking the informativeness of the examples, the best balancing of purity and informativeness remains an important question. In this paper, to solve this purity-informativeness dilemma in open-set active learning, we propose a novel Meta-Query-Net,(MQ-Net) that adaptively finds the best balancing between the two factors. Specifically, by leveraging the multi-round property of active learning, we train MQ-Net using a query set without an additional validation set. Furthermore, a clear dominance relationship between unlabeled examples is effectively captured by MQ-Net through a novel skyline regularization. Extensive experiments on multiple open-set active learning scenarios demonstrate that the proposed MQ-Net achieves 20.14% improvement in terms of accuracy, compared with the state-of-the-art methods. | - |
dc.language | English | - |
dc.publisher | Neural Information Processing Systems | - |
dc.title | Meta-Query-Net: Resolving Purity-Informativeness Dilemma in Open-set Active Learning | - |
dc.type | Conference | - |
dc.type.rims | CONF | - |
dc.citation.publicationname | 36th Conference on Neural Information Processing Systems, NeurIPS 2022 | - |
dc.identifier.conferencecountry | US | - |
dc.identifier.conferencelocation | The New Orleans Convention Center | - |
dc.contributor.localauthor | Lee, Jae-Gil | - |
dc.contributor.nonIdAuthor | Bang, Jihwan | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.