Learning Dense Contextual Features For Semantic Segmentation
| dc.contributor.author | Keleş, Hacer Yalim | |
| dc.contributor.author | Lim, Long Ang | |
| dc.contributor.department | Bilgisayar Mühendisliği | tr_TR |
| dc.contributor.faculty | Mühendislik Fakültesi | tr_TR |
| dc.date.accessioned | 2021-12-01T10:59:54Z | |
| dc.date.available | 2021-12-01T10:59:54Z | |
| dc.date.issued | 2020-06-30 | |
| dc.description.abstract | Semantic segmentation, which is one of the key problems in computer vision, has been applied in various application domains such as autonomous driving, robot navigation, or medical imagery, to name a few. Recently, deep learning, especially deep neural networks, have shown significant performance improvement over conventional semantic segmentation methods. In this paper, we present a novel encoder-decoder type deep neural network-based method, namely XSeNet, that can be trained end-to-end in a supervised manner. We adapt ResNet-50 layers as the encoder and design a cascaded decoder that composes of the stack of the X-Modules, which enables the network to learning dense contextual information and having wider field-of-view. We evaluate our method using CamVid dataset, and experimental results reveal that our method can segment most part of the scene accurately and even outperforms previous state-of-the art methods. | tr_TR |
| dc.description.index | Trdizin | tr_TR |
| dc.identifier.endpage | 34 | tr_TR |
| dc.identifier.issn/e-issn | 2618-6462 | |
| dc.identifier.issue | 1 | tr_TR |
| dc.identifier.startpage | 26 | tr_TR |
| dc.identifier.uri | http://hdl.handle.net/20.500.12575/76545 | |
| dc.identifier.volume | 62 | tr_TR |
| dc.language.iso | en | tr_TR |
| dc.publisher | Ankara Üniversitesi Fen Fakültesi | tr_TR |
| dc.relation.journal | Communications Faculty of Sciences University of Ankara Series A2-A3 Physical Sciences and Engineering | tr_TR |
| dc.relation.publicationcategory | Makale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanı | tr_TR |
| dc.subject | Semantic segmentation | tr_TR |
| dc.subject | Deep learning | tr_TR |
| dc.subject | Convolutional neural networks | tr_TR |
| dc.title | Learning Dense Contextual Features For Semantic Segmentation | tr_TR |
| dc.type | Article | tr_TR |