SEMANTIC SEGMENTATION BASED ON ITERATIVE CONTRACTION AND MERGING
檔案
本條目沒有附加檔案。
日期
2017-01-01
類型
系所
期刊名稱
2017 24TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP)
卷期與頁次
頁 1282–1286
ISSN
1522-4880
語言
英文
摘要
The state-of-the-art models for semantic image segmentation usually contain a convolutional neural network (CNN) and a conditional random field (CRF). As a predictor, existing CNN techniques can generate a dense prediction result but may generate obvious boundary errors at the same time. As a refinement model, CRF improves the CNN outcomes by forcing the consistency of local labels. However, the use of CRF may cause fragmentation effect around object boundaries. In this paper, we propose the use of a so-called iterative contraction and merging (ICM) process to facilitate the semantic segmentation process. Guided by the high-level information from CNN, the ICM process is used as a tool to grow image segments in a bottom-up way and to produce more accurate outcomes in an iterative way. The ICM process can faithfully preserve the boundary information and maintain the consistency of local labels. Our experimental results demonstrate that the performance of the proposed approach is comparable to the state-of-the-art models but with more accurate boundaries.
所屬典藏
會議論文引用此條目
Yang, T.-H., Syu, J.-H., & Wang, S.-J. (2017). SEMANTIC SEGMENTATION BASED ON ITERATIVE CONTRACTION AND MERGING. 2017 24TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), 1282–1286. https://ir.lib.nycu.edu.tw/handle/11536/147214
引用文字依 APA 第 7 版格式自動產生,使用前請再核對。
分享
永久網址:https://ir.lib.nycu.edu.tw/handle/11536/147214