Geodesic
BiSeNet-oriented context attention model for image semantic segmentation
Computer Science and Information Systems, Tome 19 (2022) no. 3.

Voir la notice de l'article provenant de la source Computer Science and Information Systems website

When the traditional semantic segmentation model is adopted, the different feature importance of feature maps is ignored in the feature extraction stage, which results in the detail loss, and affects the segmentation effect. In this paper, we propose a BiSeNet-oriented context attention model for image semantic segmenta-tion. In the BiSeNet, the spatial path is utilized to extract more low-level features to solve the problem of information loss in deep network layers. Context attention mechanism is used to mine high-level implied semantic features of images. Mean-while, the focus loss is used as the loss function to improve the final segmentation effect by reducing the internal weighting. Finally, we conduct experiments on open data sets, and the results show that pixel accuracy, average pixel accuracy, and aver-age Intersection-over-Union are greatly improved compared with other state-of-the-art semantic segmentation models. It effectively improves the accuracy of feature extraction, reduces the loss of feature details, and improves the final segmentation effect.
Keywords: image semantic segmentation, BiSeNet, context attention, focus loss 
@article{CSIS_2022_19_3_a19,
     author = {Lin Teng and Yulong Qiao},
     title = {BiSeNet-oriented context attention model for image semantic segmentation},
     journal = {Computer Science and Information Systems},
     publisher = {mathdoc},
     volume = {19},
     number = {3},
     year = {2022},
     url = {http://geodesic.mathdoc.fr/item/CSIS_2022_19_3_a19/}
}
TY  - JOUR
AU  - Lin Teng
AU  - Yulong Qiao
TI  - BiSeNet-oriented context attention model for image semantic segmentation
JO  - Computer Science and Information Systems
PY  - 2022
VL  - 19
IS  - 3
PB  - mathdoc
UR  - http://geodesic.mathdoc.fr/item/CSIS_2022_19_3_a19/
ID  - CSIS_2022_19_3_a19
ER  - 
%0 Journal Article
%A Lin Teng
%A Yulong Qiao
%T BiSeNet-oriented context attention model for image semantic segmentation
%J Computer Science and Information Systems
%D 2022
%V 19
%N 3
%I mathdoc
%U http://geodesic.mathdoc.fr/item/CSIS_2022_19_3_a19/
%F CSIS_2022_19_3_a19
Lin Teng; Yulong Qiao. BiSeNet-oriented context attention model for image semantic segmentation. Computer Science and Information Systems, Tome 19 (2022) no. 3. http://geodesic.mathdoc.fr/item/CSIS_2022_19_3_a19/