자료유형 | 학위논문 |
---|---|
서명/저자사항 | Towards Generalized Frameworks for Object Recognition. |
개인저자 | Santhanam, Venkataraman. |
단체저자명 | University of Maryland, College Park. Computer Science. |
발행사항 | [S.l.]: University of Maryland, College Park., 2018. |
발행사항 | Ann Arbor: ProQuest Dissertations & Theses, 2018. |
형태사항 | 117 p. |
기본자료 저록 | Dissertation Abstracts International 80-02B(E). Dissertation Abstract International |
ISBN | 9780438402164 |
학위논문주기 | Thesis (Ph.D.)--University of Maryland, College Park, 2018. |
일반주기 |
Source: Dissertation Abstracts International, Volume: 80-02(E), Section: B.
Adviser: Larry S. Davis. |
요약 | Over the past few years, deep convolutional neural network (DCNN) based approaches have been immensely successful in tackling a diverse range of object recognition problems. Popular DCNN architectures like deep residual networks (ResNets) are hi |
요약 | We first present a generic DCNN architecture for Im2Im regression that can be trained end-to-end without any further machinery. Our proposed architecture, the Recursively Branched Deconvolutional Network (RBDN), which features a cheap early mult |
요약 | Second, we focus on gradient flow and optimization in ResNets. In particular, we theoretically analyze why pre-activation(v2) ResNets outperform the original ResNets(v1) on CIFAR datasets but not on ImageNet. Our analysis reveals that although v |
요약 | Finally, we present a robust non-parametric probabilistic ensemble method for multi-classification, which outperforms the state-of-the-art ensemble methods on several machine learning and computer vision datasets for object recognition with st |
일반주제명 | Computer science. Artificial intelligence. |
언어 | 영어 |
바로가기 |
: 이 자료의 원문은 한국교육학술정보원에서 제공합니다. |