DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | Yoo, Changdong | - |
dc.contributor.advisor | 유창동 | - |
dc.contributor.author | Ju, Minjeong | - |
dc.date.accessioned | 2021-05-13T19:34:23Z | - |
dc.date.available | 2021-05-13T19:34:23Z | - |
dc.date.issued | 2020 | - |
dc.identifier.uri | http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=911410&flag=dissertation | en_US |
dc.identifier.uri | http://hdl.handle.net/10203/284780 | - |
dc.description | 학위논문(석사) - 한국과학기술원 : 전기및전자공학부, 2020.2,[iv, 33 p. :] | - |
dc.description.abstract | This paper proposes a Generic-Attribute-Pose Network (GAPNet) that attends spatial regions to discriminate for fine-grained visual categorization. Compared to a prototypical image classification task with reasonably large variation between classes, fine-grained visual categorization is a task that involves small inter-class variation and large intra-class variation. The GAPNet attends salient regions that can discriminate between classes, but is common within a class. The GAPNet is composed of four streams: the Generic-, Pose-, Part-, and Attribute-stream. The Generic-stream is the main-stream that attends the backbone features with respect to the pose and part-attributes by an attention module referred to as Multi-Attribute Attention Module (MAAM). The Pose-stream extracts pose-specific feature from the backbone feature, while the Part-Attribute streams output features specific pertaining to parts classified in the Pose-stream. The MAAM takes pose, part, and attribute features as query and backbone feature as key-value, and performs cross-inner dot-product between the channels of them followed by max-pooling, to attend the channels of key-value according to best matched query channel. To evaluate the performance of GAPNet, quantitative evaluation and ablation studies on Caltech-UCSD Birds (CUB-Birds) and NABirds are conducted. The functionality of the MAAM module is also verified. Moreover, the effects of each stream in GAPNet are evaluated quantitatively and qualitatively. The influence of stream-order applied to the backbone feature is analyzed. The experiments for GAPNet based on weakly-supervised methods without part annotations are implemented. | - |
dc.language | eng | - |
dc.publisher | 한국과학기술원 | - |
dc.subject | Fine-Grained Visual Categorization▼aMulti-Task Learning▼aAttention Module▼aComputer Vision▼aDeep Learning | - |
dc.subject | 세부 카테고리 분류▼a다중과제 학습▼a어텐션 모듈▼a컴퓨터 비전▼a딥러닝 | - |
dc.title | GAPNet | - |
dc.title.alternative | 세부 카테고리 분류를 위한 다중 특성 어텐션 모듈을 이용한 일반-특성-포즈 네트워크 | - |
dc.type | Thesis(Master) | - |
dc.identifier.CNRN | 325007 | - |
dc.description.department | 한국과학기술원 :전기및전자공학부, | - |
dc.contributor.alternativeauthor | 주민정 | - |
dc.title.subtitle | generic-attribute-ppse network for fine-grained visual categorization using multi-attribute attention module | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.