Local Context Attention for Salient Object Segmentation
| العنوان: | Local Context Attention for Salient Object Segmentation |
|---|---|
| المؤلفون: | Zhengyi Lv, Yuwen He, Pengfei Xiong, Kuntao Xiao, Jing Tan |
| المصدر: | Computer Vision – ACCV 2020 ISBN: 9783030695248 ACCV (1) |
| بيانات النشر: | Springer International Publishing, 2021. |
| سنة النشر: | 2021 |
| مصطلحات موضوعية: | Structure (mathematical logic), business.industry, Computer science, Context (language use), Pattern recognition, 02 engineering and technology, 010501 environmental sciences, Texture (music), 01 natural sciences, Correlation, Feature (computer vision), 0202 electrical engineering, electronic engineering, information engineering, 020201 artificial intelligence & image processing, Segmentation, Artificial intelligence, Architecture, business, 0105 earth and related environmental sciences, Block (data storage) |
| الوصف: | Salient object segmentation aims at distinguishing various salient objects from backgrounds. Despite the lack of semantic consistency, salient objects often have obvious texture and location characteristics in local area. Based on this priori, we propose a novel Local Context Attention Network (LCANet) to generate locally reinforcement feature maps in a uniform representational architecture. The proposed network introduces an Attentional Correlation Filter (ACF) module to generate explicit local attention by calculating the correlation feature map between coarse prediction and global context. Then it is expanded to a Local Context Block (LCB). Furthermore, a one-stage coarse-to-fine structure is implemented based on LCB to adaptively enhance the local context description ability. Comprehensive experiments are conducted on several salient object segmentation datasets, demonstrating the superior performance of the proposed LCANet against the state-of-the-art methods, especially with 0.883 max F-score and 0.034 MAE on DUTS-TE dataset. |
| ردمك: | 978-3-030-69524-8 |
| URL الوصول: | https://explore.openaire.eu/search/publication?articleId=doi_________::790b9076a588dcc609bf62414ce21479 https://doi.org/10.1007/978-3-030-69525-5_42 |
| حقوق: | OPEN |
| رقم الأكسشن: | edsair.doi...........790b9076a588dcc609bf62414ce21479 |
| قاعدة البيانات: | OpenAIRE |
| ردمك: | 9783030695248 |
|---|