DC Field | Value | Language |
---|---|---|
dc.contributor.author | Kim, Junho | ko |
dc.contributor.author | Kim, Minsu | ko |
dc.contributor.author | Kim, Jung Uk | ko |
dc.contributor.author | Lee, Hong Joo | ko |
dc.contributor.author | Lee, Sangmin | ko |
dc.contributor.author | Hong, Joanna | ko |
dc.contributor.author | Ro, Yong Man | ko |
dc.date.accessioned | 2020-06-26T03:20:25Z | - |
dc.date.available | 2020-06-26T03:20:25Z | - |
dc.date.created | 2020-05-18 | - |
dc.date.created | 2020-05-18 | - |
dc.date.created | 2020-05-18 | - |
dc.date.created | 2020-05-18 | - |
dc.date.issued | 2020-10-25 | - |
dc.identifier.citation | IEEE International Conference on Image Processing (ICIP) 2020, pp.1791 - 1795 | - |
dc.identifier.issn | 1522-4880 | - |
dc.identifier.uri | http://hdl.handle.net/10203/274932 | - |
dc.description.abstract | Few-shot classification is defined as a task where the network aims to classify unseen classes given only a few samples. Recent approaches, especially metric-based methods, have great progress in few-shot classification. However, the existing metric-based methods have a limitation in deploying discriminative features for elaborate comparison. They usually extract features from the embedding network without direct consideration of the relationship between support and query sets. To address the relationship, we propose a novel architecture, Style Correlated Module (SCM) to learn style correlation between support and query sets for few-shot classification. The proposed module leads support and query feature maps to focus on significant style correlated features and encourage the metric network to conduct an elaborate comparison. Furthermore, the proposed module can be generally applied to the existing metric-based approaches by adding the SCM behind the embedding network. We evaluate our proposed method with comprehensive experiments on two publicly available datasets and demonstrate its effectiveness with comparable results. | - |
dc.language | English | - |
dc.publisher | IEEE Signal Processing Society | - |
dc.title | Learning Style Correlation For Elaborate Few-Shot Classification | - |
dc.type | Conference | - |
dc.identifier.wosid | 000646178501179 | - |
dc.identifier.scopusid | 2-s2.0-85098619095 | - |
dc.type.rims | CONF | - |
dc.citation.beginningpage | 1791 | - |
dc.citation.endingpage | 1795 | - |
dc.citation.publicationname | IEEE International Conference on Image Processing (ICIP) 2020 | - |
dc.identifier.conferencecountry | AR | - |
dc.identifier.conferencelocation | Abu Dhabi National Exhibition Center (ADNEC), Abu Dhabi, United Arab Emirates (UAE) | - |
dc.identifier.doi | 10.1109/ICIP40778.2020.9190685 | - |
dc.contributor.localauthor | Ro, Yong Man | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.