DC Field | Value | Language |
---|---|---|
dc.contributor.author | Cho, Jae Won | ko |
dc.contributor.author | Kim, Dong-Jin | ko |
dc.contributor.author | Choi, Jinsoo | ko |
dc.contributor.author | Jung, Yunjae | ko |
dc.contributor.author | Kweon, In-So | ko |
dc.date.accessioned | 2023-09-05T12:01:14Z | - |
dc.date.available | 2023-09-05T12:01:14Z | - |
dc.date.created | 2023-09-05 | - |
dc.date.issued | 2021-06 | - |
dc.identifier.citation | 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) | - |
dc.identifier.issn | 2160-7508 | - |
dc.identifier.uri | http://hdl.handle.net/10203/312241 | - |
dc.description.abstract | In this work, we address the issues of the missing modalities that have arisen from the Visual Question Answer-Difference prediction task and find a novel method to solve the task at hand. We address the missing modality-the ground truth answers-that are not present at test time and use a privileged knowledge distillation scheme to deal with the issue of the missing modality. In order to efficiently do so, we first introduce a model, the "Big" Teacher, that takes the image/question/answer triplet as its input and outperforms the baseline, then use a combination of models to distill knowledge to a target network (student) that only takes the image/question pair as its inputs. We experiment our models on the VizWiz and VQA-V2 Answer Difference datasets and show through extensive experimentation and ablation the performance of our method and a diverse possibility for future research. | - |
dc.language | English | - |
dc.publisher | IEEE | - |
dc.title | Dealing with Missing Modalities in the Visual Question Answer-Difference Prediction Task through Knowledge Distillation | - |
dc.type | Conference | - |
dc.identifier.wosid | 000705890201074 | - |
dc.identifier.scopusid | 2-s2.0-85112519740 | - |
dc.type.rims | CONF | - |
dc.citation.publicationname | 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) | - |
dc.identifier.conferencecountry | US | - |
dc.identifier.conferencelocation | Nashville, TN | - |
dc.identifier.doi | 10.1109/cvprw53098.2021.00175 | - |
dc.contributor.localauthor | Kweon, In-So | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.