repository
Width and height based spatial distribution pooling networks for unsupervised domain adaptation
| DC Field | Value | Language |
|---|---|---|
| dc.contributor.advisor | 황원준 | - |
| dc.contributor.author | 윤진수 | - |
| dc.date.accessioned | 2022-11-29T03:01:09Z | - |
| dc.date.available | 2022-11-29T03:01:09Z | - |
| dc.date.issued | 2022-08 | - |
| dc.identifier.other | 31942 | - |
| dc.identifier.uri | https://dspace.ajou.ac.kr/handle/2018.oak/20812 | - |
| dc.description | 학위논문(석사)--아주대학교 일반대학원 :인공지능학과,2022. 8 | - |
| dc.description.tableofcontents | Ⅰ. Introduction 1 Ⅱ. Related Work 5 Ⅲ. Proposed Method 8 A. Background 8 B. Proposed Method 8 1. Baseline 8 2. Sum pooling 11 3. Consistency Regularization 13 4. Loss functions 13 Ⅳ. Experimental results and discussion 16 A. Datasets 16 B. Implementation details 18 C. Evaluation in Classification 18 D. Evaluation in Object detection 20 E. Discussion 23 Ⅴ. Conclusion 25 Reference 26 | - |
| dc.language.iso | eng | - |
| dc.publisher | The Graduate School, Ajou University | - |
| dc.rights | 아주대학교 논문은 저작권에 의해 보호받습니다. | - |
| dc.title | Width and height based spatial distribution pooling networks for unsupervised domain adaptation | - |
| dc.type | Thesis | - |
| dc.contributor.affiliation | 아주대학교 일반대학원 | - |
| dc.contributor.alternativeName | Jinsu Yun | - |
| dc.contributor.department | 일반대학원 인공지능학과 | - |
| dc.date.awarded | 2022. 8 | - |
| dc.description.degree | Master | - |
| dc.identifier.localId | 1254258 | - |
| dc.identifier.uci | I804:41038-000000031942 | - |
| dc.identifier.url | https://dcoll.ajou.ac.kr/dcollection/common/orgView/000000031942 | - |
| dc.subject.keyword | Unsupervised Domain Adaptation | - |
| dc.description.alternativeAbstract | Unsupervised Domain Adaption, which was recently developed, focuses on the adaptation of knowledge from labeled source data to unlabeled target data. Domain adaptation is an approach that efficiently adapts a new model to different environments where the source and target domains are similar but not identical. By adapting the information from the source domain to the target domain, it improves the probability of enhancing performance. However, the majority of the research were plagued by a domain shift issue. They neglect crucial areas that correspond to the image. To minimize the domain gap in unsupervised domain adaptation, we suggest a simple yet efficient spatial distribution-based Sum pooling approach and Consistency regularization in this paper. The sum pooling approach integrates information taken from the model in both the height and width axes. Consistency regularization avoids sum pooling divergence and tackles the domain shift problem by shortening the distance between the feature of encoder and the sum pooling feature. We evaluate our technique on datasets such as MNIST, MNIST-M, SVHN for classification tasks, and Cityscapes, Foggy Cityscape, Sim10k, and KITTI for object detection tasks. The results show that our proposed approach is helpful in decreasing the distance between the source and target domains. | - |
- Appears in Collections:
- Graduate School of Ajou University > Department of Artificial Intelligence > 3. Theses(Master)
- Files in This Item:
- There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.
-
- License
- STATISTICS
- Total Visit :3,720,693
- Total Download :1,818
- Today View :3,896
