https://scholars.lib.ntu.edu.tw/handle/123456789/632364
標題: | INTERACTIVE OBJECT segmentation WITH DYNAMIC CLICK TRANSFORM | 作者: | Lin C.-T Tu W.-C Liu C.-T SHAO-YI CHIEN |
關鍵字: | Computer vision; Convolutional neural network; Interactive segmentation | 公開日期: | 2021 | 卷: | 2021-September | 起(迄)頁: | 2284-2288 | 來源出版物: | Proceedings - International Conference on Image Processing, ICIP | 摘要: | In the interactive segmentation, users initially click on the target object to segment the main body and then provide corrections on mislabeled regions to iteratively refine the segmentation masks. Most existing methods transform these user-provided clicks into interaction maps and concatenate them with image as the input tensor. Typically, the interaction maps are determined by measuring the distance of each pixel to the clicked points, ignoring the relation between clicks and mislabeled regions. We propose a Dynamic Click Transform Network (DCT-Net), consisting of Spatial-DCT and Feature-DCT, to better represent user interactions. Spatial-DCT transforms each user-provided click with individual diffusion distance according to the target scale, and Feature-DCT normalizes the extracted feature map to a specific distribution predicted from the clicked points. We demonstrate the effectiveness of our proposed method and achieve favorable performance compared to the state-of-the-art on three standard benchmark datasets. © 2021 IEEE |
URI: | https://www.scopus.com/inward/record.uri?eid=2-s2.0-85125591659&doi=10.1109%2fICIP42928.2021.9506678&partnerID=40&md5=f89fd86d692d544fa7fa84f49bede7e9 https://scholars.lib.ntu.edu.tw/handle/123456789/632364 |
ISSN: | 15224880 | DOI: | 10.1109/ICIP42928.2021.9506678 |
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。