DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | Lee, Heung-Kyu | - |
dc.contributor.advisor | 이흥규 | - |
dc.contributor.author | Jang, Heeoh | - |
dc.date.accessioned | 2021-05-13T19:32:31Z | - |
dc.date.available | 2021-05-13T19:32:31Z | - |
dc.date.issued | 2020 | - |
dc.identifier.uri | http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=911008&flag=dissertation | en_US |
dc.identifier.uri | http://hdl.handle.net/10203/284677 | - |
dc.description | 학위논문(석사) - 한국과학기술원 : 전산학부, 2020.2,[iv, 30 p. :] | - |
dc.description.abstract | Recently, object detection has presented superior performance using the deep convolutional neural network (CNN). However, most CNN-based models need the bounding box information of the input image in pairs. To overcome this limitation, we propose the Generative Object Detection which learns with only cropped images that are not in pairs. Our model based on Generative Adversarial Networks (GAN) creates cropped images by making a mask that represents the object region. To achieve this goal, we devise a novel mask mean loss (MML) that helps the GAN be able to estimate the distribution of training data and uses dilated convolution for a wider reception eld in the generator. The experimental results show that Generative Object Detection improves mIoU and accuracy. | - |
dc.language | eng | - |
dc.publisher | 한국과학기술원 | - |
dc.subject | Object Detection▼aGenerative Adversarial Networks▼aDeep-learning▼aUnsupervised learning▼aComputer Vision | - |
dc.subject | 물체인식▼a적대적 생성 신경망▼a딥러닝▼a비지도학습법▼a컴퓨터비전 | - |
dc.title | Object detection based on generative adversarial networks | - |
dc.title.alternative | 물체 인식을 위한 적대적 생성 신경망 연구 : 딥러닝 기반의 비지도 학습법 | - |
dc.type | Thesis(Master) | - |
dc.identifier.CNRN | 325007 | - |
dc.description.department | 한국과학기술원 :전산학부, | - |
dc.contributor.alternativeauthor | 장희오 | - |
dc.title.subtitle | unsupervised deep learning approaches | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.