eprintid: 3264 rev_number: 18 eprint_status: archive userid: 335 dir: disk0/00/00/32/64 datestamp: 2018-12-14 08:16:21 lastmod: 2018-12-14 08:16:21 status_changed: 2018-12-14 08:16:21 type: conference_item metadata_visibility: show creators_name: Bui, Duc Thinh creators_name: Nguyen, Do Van creators_name: Nguyen, Thi Thu Thuy creators_name: Tran, Quoc Long creators_name: Le, Thanh Ha creators_id: thinh.ducbui@gmail.com creators_id: ngdovan@gmail.com creators_id: myngthuy@gmail.com creators_id: tqlong@vnu.edu.vn creators_id: ltha@vnu.edu.vn title: Aerial Image Semantic Segmentation Using Neural Search Network Architecture ispublished: pub subjects: IT divisions: fac_fit abstract: In remote sensing data analysis and computer vision, aerial image segmentation is a crucial research topic, which has many appli- cations in environmental and urban planning. Recently, deep learning is using to tackle many computer vision problem, including aerial image segmentation. Results have shown that deep learning gains much higher accuracy than other methods on many benchmark data sets. In this work, we propose a neural network called NASNet-FCN, which based on Fully Convolutional Network - a frame work for solving semantic segmenta- tion problem and image feature extractor derived from state-of-the-art object recognition network called Neural Search Network Architecture. Our networks are trained and judged by using benchmark dataset from ISPRS Vaihingen challenge. Results show that our methods achieved state-of-the-art accuracy with potential improvements. date: 2018-11-19 date_type: published full_text_status: public pres_type: paper event_title: (MIWAI 2018) 12th Multi-disciplinary International Conference on Artificial Intelligence event_location: Hanoi, Vietnam event_dates: 18-20th November 2018 event_type: conference refereed: TRUE citation: Bui, Duc Thinh and Nguyen, Do Van and Nguyen, Thi Thu Thuy and Tran, Quoc Long and Le, Thanh Ha (2018) Aerial Image Semantic Segmentation Using Neural Search Network Architecture. In: (MIWAI 2018) 12th Multi-disciplinary International Conference on Artificial Intelligence, 18-20th November 2018, Hanoi, Vietnam. document_url: https://eprints.uet.vnu.edu.vn/eprints/id/eprint/3264/1/Thinh_miwai_0703_paper.pdf