Rethinking the U-Shape Structure for Salient Object Detection
| العنوان: | Rethinking the U-Shape Structure for Salient Object Detection |
|---|---|
| المؤلفون: | Ming-Ming Cheng, Zhi-Ang Liu, Pai Peng, Jiang-Jiang Liu |
| المصدر: | IEEE Transactions on Image Processing. 30:9030-9042 |
| بيانات النشر: | Institute of Electrical and Electronics Engineers (IEEE), 2021. |
| سنة النشر: | 2021 |
| مصطلحات موضوعية: | Structure (mathematical logic), Source code, Computational complexity theory, Computer science, media_common.quotation_subject, Feature extraction, Aggregate (data warehouse), Process (computing), computer.software_genre, Computer Graphics and Computer-Aided Design, Object detection, Data mining, computer, Software, media_common, Interpolation |
| الوصف: | The U-shape structure has shown its advantage in salient object detection for efficiently combining multi-scale features. However, most existing U-shape-based methods focused on improving the bottom-up and top-down pathways while ignoring the connections between them. This paper shows that we can achieve the cross-scale information interaction by centralizing these connections, hence obtaining semantically stronger and positionally more precise features. To inspire the newly proposed strategy's potential, we further design a relative global calibration module that can simultaneously process multi-scale inputs without spatial interpolation. Our approach can aggregate features more effectively while introducing only a few additional parameters. Our approach can cooperate with various existing U-shape-based salient object detection methods by substituting the connections between the bottom-up and top-down pathways. Experimental results demonstrate that our proposed approach performs favorably against the previous state-of-the-arts on five widely used benchmarks with less computational complexity. The source code will be publicly available. |
| تدمد: | 1941-0042 1057-7149 |
| DOI: | 10.1109/tip.2021.3122093 |
| URL الوصول: | https://explore.openaire.eu/search/publication?articleId=doi_dedup___::3ea57e8f02813fa8db436712fdd9a526 https://doi.org/10.1109/tip.2021.3122093 |
| Rights: | CLOSED |
| رقم الانضمام: | edsair.doi.dedup.....3ea57e8f02813fa8db436712fdd9a526 |
| قاعدة البيانات: | OpenAIRE |
| تدمد: | 19410042 10577149 |
|---|---|
| DOI: | 10.1109/tip.2021.3122093 |