https://scholars.lib.ntu.edu.tw/handle/123456789/640572
標題: | Multi-Scale Receptive Field Attention Free Transformer Feature Extractor | 作者: | Cheng, Min Hsuan JIAN-JIUN DING Hua, Shiang Chih |
關鍵字: | attention free transformer | dilation convolution | feature extractor | U-net | weakly supervised | 公開日期: | 1-一月-2023 | 來源出版物: | 2023 IEEE International Conference on Visual Communications and Image Processing, VCIP 2023 | 摘要: | Image feature point extraction is critical in several computer vision tasks like object detection, image stitching, visual re-localization, 3D reconstruction, and simultaneous localization and mapping (SLAM). In recent years, learning-based feature extractor approaches have become increasingly prevalent in computer vision and can achieve even better matching performance. Nevertheless, how to label and describe the discriminative feature is problematic. In this paper, we proposed a weakly-supervised learning approach that integrates a transformer and U-net-like convolution networks to better consider global and local contexts. Moreover, we concatenate multiple-size dilation convolutions to achieve a wider receptive field. Experiments show that the proposed approach has a performance and is robust to viewpoint change and illumination variation. |
URI: | https://scholars.lib.ntu.edu.tw/handle/123456789/640572 | ISBN: | 9798350359855 | DOI: | 10.1109/VCIP59821.2023.10402766 |
顯示於: | 電機工程學系 |
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。