Distortion-aware network pruning and feature reuse for real-time video segmentation실시간 의미론적 영상 분할을 위한 왜곡 인식 신경망 가지치기와 특징 재사용

Cited 0 time in webofscience Cited 0 time in scopus
  • Hit : 211
  • Download : 0
DC FieldValueLanguage
dc.contributor.advisorHwang, Sung Ju-
dc.contributor.advisor황성주-
dc.contributor.authorRhee, Hyunsu-
dc.date.accessioned2023-06-22T19:31:30Z-
dc.date.available2023-06-22T19:31:30Z-
dc.date.issued2023-
dc.identifier.urihttp://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=1032327&flag=dissertationen_US
dc.identifier.urihttp://hdl.handle.net/10203/308235-
dc.description학위논문(석사) - 한국과학기술원 : 김재철AI대학원, 2023.2,[iii, 24 p. :]-
dc.description.abstractReal-time video segmentation is a crucial task for many real-world applications such as autonomous driving and robot control. Since state-of-the-art semantic segmentation models are often too heavy for real-time applications despite their impressive performance, researchers have proposed lightweight architectures with speed-accuracy trade-offs, achieving real-time speed at the expense of reduced accuracy. In this paper, we propose a novel framework to speed up any architecture with skip-connections for real-time vision tasks by exploiting the temporal locality in videos. Specifically, at the arrival of each frame, we transform the features from the previous frame to reuse them at specific spatial bins. We then perform partial computation of the backbone network on the regions of the current frame that captures temporal differences between the current and previous frame. This is done by dynamically dropping out residual blocks using a gating mechanism which decides which blocks to drop based on inter-frame distortion. We validate our Spatial-Temporal Mask Generator (STMG) on video semantic segmentation benchmarks with multiple backbone networks, and show that our method largely speeds up inference with minimal loss of accuracy.-
dc.languageeng-
dc.publisher한국과학기술원-
dc.subjectSemantic segmentation▼aReal-time vision▼aNetwork pruning-
dc.subject의미론적 분할▼a실시간 시각인식▼a신경망 가지치기-
dc.titleDistortion-aware network pruning and feature reuse for real-time video segmentation-
dc.title.alternative실시간 의미론적 영상 분할을 위한 왜곡 인식 신경망 가지치기와 특징 재사용-
dc.typeThesis(Master)-
dc.identifier.CNRN325007-
dc.description.department한국과학기술원 :김재철AI대학원,-
dc.contributor.alternativeauthor이현수-
Appears in Collection
AI-Theses_Master(석사논문)
Files in This Item
There are no files associated with this item.

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0