Interactive semantic segmentation of aerial images with deep neural networks / Segmentation sémantique interactive d'images aériennes avec des réseaux de neurones profonds
👁 2 lượt xem↓ 0 lượt tải qua VietLexVietLex bảo vệ quyền riêng tư của bạn — không tracking, không chia sẻ thông tin tải về cho bên thứ ba.
📑 Trích dẫn đầy đủ (citation)
APA-like:
Tác giả chưa xác định. Interactive semantic segmentation of aerial images with deep neural networks / Segmentation sémantique interactive d'images aériennes avec des réseaux de neurones profonds. Thesis, HAL - Pháp.
Việt Nam (chuẩn TCVN 5453:1991):
. Interactive semantic segmentation of aerial images with deep neural networks / Segmentation sémantique interactive d'images aériennes avec des réseaux de neurones profonds. Thesis. HAL - Pháp. Truy cập từ .
Tóm tắt
We propose in this thesis to build up a collaboration between a deep neural network and a human in the loop to swiftly collect accurate segmentation maps of remote sensing images. In a nutshell, the user iteratively interacts with the network to correct its initially flawed predictions. Concretely, these interactions are annotations representing the semantic labels. Our contributions are fourfold. First, we propose two interactive learning schemes to integrate user inputs into deep neural networ...