DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | Hwang, Sung Ju | - |
dc.contributor.advisor | 황성주 | - |
dc.contributor.author | Bruno, Andries | - |
dc.date.accessioned | 2021-05-13T19:32:40Z | - |
dc.date.available | 2021-05-13T19:32:40Z | - |
dc.date.issued | 2020 | - |
dc.identifier.uri | http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=911021&flag=dissertation | en_US |
dc.identifier.uri | http://hdl.handle.net/10203/284686 | - |
dc.description | 학위논문(석사) - 한국과학기술원 : 전산학부, 2020.2,[iv, 35 p. :] | - |
dc.description.abstract | We tackle the problem of realtime latency reduction in huge deep neural networks for the tasks of semantic segmentation and video object detection. Input dependent or conditional computation is employed to dynamically generate connectivity paths in a neural network for a given input. We also employ forecasting of unseen feature maps in cases where it is easier to generate such feature maps and avoid the expensive computation of backbone networks. Finally, we explore the utilization of a tracker and couple with a slow but accurate object detector using a reinforcement learning scheduling routine. | - |
dc.language | eng | - |
dc.publisher | 한국과학기술원 | - |
dc.subject | Semantic Segmentation▼aConditional Computation▼aVideo Object Detection▼aTracking | - |
dc.subject | 이미지 세그멘테이션▼a조건부 연산(딥러닝 가속화)▼a영상에서의 물체 검출▼a트래킹 | - |
dc.title | Video object detection and segmentation | - |
dc.title.alternative | 비디오 물체 탐지와 세그먼테이션 | - |
dc.type | Thesis(Master) | - |
dc.identifier.CNRN | 325007 | - |
dc.description.department | 한국과학기술원 :전산학부, | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.