TY - GEN
T1 - MPNet
T2 - 14th International Conference on Ubiquitous and Future Networks, ICUFN 2023
AU - Quyen, Van Toan
AU - Kim, Min Young
N1 - Publisher Copyright:
© 2023 IEEE.
PY - 2023
Y1 - 2023
N2 - Semantic segmentation is a complex topic where they assign each pixel of an image with a corresponding class and demand accuracy at objective boundaries. The method plays a vital role in scene-understanding scenarios. For self-driving applications, the input source includes various types of objects such as trucks, people, or traffic signs. One receptive field is only effective in capturing a short range of sizes. Feature pyramid network (FPN) utilizes different fields of view to extract information from the input. The FPN approach obtains the spatial information from the high-resolution feature map and the semantic information from the lower scales. The final feature representation contains coarse and fine details, but it has some drawbacks. They burden the system with extensive computation and reduce the semantic information. In this paper, we devise an effective multiscale predictions network (MPNet) to address these issues. A multiscale pyramid of predictions effectively processes the prominent characteristics of each feature. A pair of adjacent features is combined together to predict the output separately. A lower-scale feature of each prediction is assigned as the contextual contributor, and the other provides coarser information. The contextual branch is passed through the atrous spatial pyramid pooling to improve performance. The segmentation scores are fused to obtain advantages from all predictions. The model is validated by a series of experiments on open data sets. We have achieved good results 76.5% mIoU at 50 FPS on Cityscapes and 43.9% mIoU on Mapillary Vistas.
AB - Semantic segmentation is a complex topic where they assign each pixel of an image with a corresponding class and demand accuracy at objective boundaries. The method plays a vital role in scene-understanding scenarios. For self-driving applications, the input source includes various types of objects such as trucks, people, or traffic signs. One receptive field is only effective in capturing a short range of sizes. Feature pyramid network (FPN) utilizes different fields of view to extract information from the input. The FPN approach obtains the spatial information from the high-resolution feature map and the semantic information from the lower scales. The final feature representation contains coarse and fine details, but it has some drawbacks. They burden the system with extensive computation and reduce the semantic information. In this paper, we devise an effective multiscale predictions network (MPNet) to address these issues. A multiscale pyramid of predictions effectively processes the prominent characteristics of each feature. A pair of adjacent features is combined together to predict the output separately. A lower-scale feature of each prediction is assigned as the contextual contributor, and the other provides coarser information. The contextual branch is passed through the atrous spatial pyramid pooling to improve performance. The segmentation scores are fused to obtain advantages from all predictions. The model is validated by a series of experiments on open data sets. We have achieved good results 76.5% mIoU at 50 FPS on Cityscapes and 43.9% mIoU on Mapillary Vistas.
KW - Semantic segmentation
KW - feature pyramid network
KW - multiscale prediction
KW - real-time application
UR - http://www.scopus.com/inward/record.url?scp=85169289837&partnerID=8YFLogxK
U2 - 10.1109/ICUFN57995.2023.10199608
DO - 10.1109/ICUFN57995.2023.10199608
M3 - Conference contribution
AN - SCOPUS:85169289837
T3 - International Conference on Ubiquitous and Future Networks, ICUFN
SP - 114
EP - 119
BT - ICUFN 2023 - 14th International Conference on Ubiquitous and Future Networks
PB - IEEE Computer Society
Y2 - 4 July 2023 through 7 July 2023
ER -