کد مقاله | کد نشریه | سال انتشار | مقاله انگلیسی | نسخه تمام متن |
---|---|---|---|---|
6938946 | 1449967 | 2018 | 10 صفحه PDF | دانلود رایگان |
عنوان انگلیسی مقاله ISI
Deep contextual recurrent residual networks for scene labeling
ترجمه فارسی عنوان
شبکه های باقی مانده عمیق متناظر باقی مانده برای برچسب گذاری صحنه
دانلود مقاله + سفارش ترجمه
دانلود مقاله ISI انگلیسی
رایگان برای ایرانیان
کلمات کلیدی
شبکه مجازی یادگیری باقی مانده، نمایش بصری، مدل سازی زمینه، برچسب زدن صحنه
موضوعات مرتبط
مهندسی و علوم پایه
مهندسی کامپیوتر
چشم انداز کامپیوتر و تشخیص الگو
چکیده انگلیسی
Designed as extremely deep architectures, deep residual networks which provide a rich visual representation and offer robust convergence behaviors have recently achieved exceptional performance in numerous computer vision problems. Being directly applied to a scene labeling problem, however, they were limited to capture long-range contextual dependence, which is a critical aspect. To address this issue, we propose a novel approach, Contextual Recurrent Residual Networks (CRRN) which is able to simultaneously handle rich visual representation learning and long-range context modeling within a fully end-to-end deep network. Furthermore, our proposed end-to-end CRRN is completely trained from scratch, without using any pre-trained models in contrast to most existing methods usually fine-tuned from the state-of-the-art pre-trained models, e.g. VGG-16, ResNet, etc. The experiments are conducted on four challenging scene labeling datasets, i.e. SiftFlow, CamVid, Stanford background and SUN datasets, and compared against various state-of-the-art scene labeling methods.
ناشر
Database: Elsevier - ScienceDirect (ساینس دایرکت)
Journal: Pattern Recognition - Volume 80, August 2018, Pages 32-41
Journal: Pattern Recognition - Volume 80, August 2018, Pages 32-41
نویسندگان
T. Hoang Ngan Le, Chi Nhan Duong, Ligong Han, Khoa Luu, Kha Gia Quach, Marios Savvides,