https://scholars.lib.ntu.edu.tw/handle/123456789/413036
標題: | Cross-domain hallucination network for fine-grained object recognition | 作者: | Lin J.-F. Lin Y.-L. King E.-K. Su H.-T. Hsu W.H. |
關鍵字: | cross-domain; fine-grained classification; hallucination | 公開日期: | 2018 | 卷: | 2018-June | 起(迄)頁: | 1295-1302 | 來源出版物: | IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops | 摘要: | Existing fine-grained object recognition methods often require high-resolution images to better discriminate the subordinate classes. However, this assumption does not always hold in current surveillance systems, where the distinguished parts may not be clearly presented. Besides, data insufficiency and class imbalance make the problem even more challenging. In this paper, we leverage high-resolution images collected from Internet to improve the vehicle recognition in the surveillance environments. A cross-domain hallucination network is proposed to minimize the domain discrepancy and enhance the quality of low-resolution surveillance images. To better align the cross-domain features and boost the recognition performance, we extend the original framework to part-based hallucination networks, where the parts are automatically extracted based on the maximum responses from the convolution filters. We evaluate our method on a public surveillance vehicle dataset (BoxCars21k). Experimental results demonstrate that our approach outperforms the state-of-the-art methods. ? 2018 IEEE. |
URI: | https://scholars.lib.ntu.edu.tw/handle/123456789/413036 | ISBN: | 9781538661000 | ISSN: | 21607508 | DOI: | 10.1109/CVPRW.2018.00167 |
顯示於: | 資訊工程學系 |
檔案 | 描述 | 大小 | 格式 | |
---|---|---|---|---|
Lin_Cross-Domain_Hallucination_Network_CVPR_2018_paper.pdf | 665.18 kB | Adobe PDF | 檢視/開啟 |
在 IR 系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。