DC Field | Value | Language |
---|---|---|
dc.contributor.author | Jeong, Yongseop | ko |
dc.contributor.author | Park, Jinsun | ko |
dc.contributor.author | Cho, Donghyeon | ko |
dc.contributor.author | Hwang, Yoonjin | ko |
dc.contributor.author | Choi, Seibum B. | ko |
dc.contributor.author | Kweon, In So | ko |
dc.date.accessioned | 2022-10-25T09:02:47Z | - |
dc.date.available | 2022-10-25T09:02:47Z | - |
dc.date.created | 2022-10-25 | - |
dc.date.created | 2022-10-25 | - |
dc.date.issued | 2022-10 | - |
dc.identifier.citation | SENSORS, v.22, no.19 | - |
dc.identifier.issn | 1424-8220 | - |
dc.identifier.uri | http://hdl.handle.net/10203/299111 | - |
dc.description.abstract | Depth perception capability is one of the essential requirements for various autonomous driving platforms. However, accurate depth estimation in a real-world setting is still a challenging problem due to high computational costs. In this paper, we propose a lightweight depth completion network for depth perception in real-world environments. To effectively transfer a teacher's knowledge, useful for the depth completion, we introduce local similarity-preserving knowledge distillation (LSPKD), which allows similarities between local neighbors to be transferred during the distillation. With our LSPKD, a lightweight student network is precisely guided by a heavy teacher network, regardless of the density of the ground-truth data. Experimental results demonstrate that our method is effective to reduce computational costs during both training and inference stages while achieving superior performance over other lightweight networks. | - |
dc.language | English | - |
dc.publisher | MDPI | - |
dc.title | Lightweight Depth Completion Network with Local Similarity-Preserving Knowledge Distillation | - |
dc.type | Article | - |
dc.identifier.wosid | 000868012900001 | - |
dc.identifier.scopusid | 2-s2.0-85139962041 | - |
dc.type.rims | ART | - |
dc.citation.volume | 22 | - |
dc.citation.issue | 19 | - |
dc.citation.publicationname | SENSORS | - |
dc.identifier.doi | 10.3390/s22197388 | - |
dc.contributor.localauthor | Choi, Seibum B. | - |
dc.contributor.localauthor | Kweon, In So | - |
dc.description.isOpenAccess | N | - |
dc.type.journalArticle | Article | - |
dc.subject.keywordAuthor | depth completion | - |
dc.subject.keywordAuthor | local similarity | - |
dc.subject.keywordAuthor | knowledge distillation | - |
dc.subject.keywordAuthor | model compression | - |
dc.subject.keywordAuthor | sensor fusion | - |
dc.subject.keywordAuthor | multimodal learning | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.