What question did this study set out to answer?

This research aims to develop an efficient model for real-time semantic segmentation in driving scenes.

January 20, 2026Scientific ReportsOpen Access

Real-time semantic segmentation of driving scenes via effective attention-based information fusion and hybrid encoder

View Full Paper

Ask AI

Bookmark

Authors

CCCristina CăruntaPolytechnic University of Timişoara ACAlina CăruntaWest University of Timişoara AMAlexandru-Eugeniu MizeranschiArad County Clinical Hospital

Discussion

Member takes

Implication

Novel lightweight convolutional neural network improves semantic segmentation performance in autonomous driving, indicating faster processing and accuracy gains.

Key Points

This research aims to develop an efficient model for real-time semantic segmentation in driving scenes.
Proposed a lightweight convolutional neural network architecture named RTSSNet.
Utilized dilated convolutions in encoder stages for enhanced contextual information extraction.
Designed a lightweight decoder based on attention mechanisms to recover spatial details.
Achieved 78.3% mIoU at 121.15 FPS on the Cityscapes validation set.
Attained 77.53% mIoU at 120.68 FPS on the CamVid test set.

Cite This Study

Cărunta et al. (2026) studied this question.

synapsesocial.com/papers/696ed06d6d8d470fca57ab74 https://doi.org/10.1038/s41598-025-29931-1

View Full Paper

Ask AI

Bookmark

Implication

Novel lightweight convolutional neural network improves semantic segmentation performance in autonomous driving, indicating faster processing and accuracy gains.

Real-time semantic segmentation of driving scenes via effective attention-based information fusion and hybrid encoder

Discussion

Member takes

Implication

Key Points

Cite This Study

Real-time semantic segmentation of driving scenes via effective attention-based information fusion and hybrid encoder

Discussion

Member takes

Implication

Key Points

Cite This Study

Also Consider

Also Consider