ETRI-Knowledge Sharing Plaform



논문 검색
구분 SCI
연도 ~ 키워드


학술지 Accelerator-Aware Fast Spatial Feature Network for Real-Time Semantic Segmentation
Cited 1 time in scopus Download 7 time Share share facebook twitter linkedin kakaostory
김민종, 박병재, 지수영
IEEE Access, v.8, pp.2169-3536
20PS1400, 세라믹산업 제조혁신을 위한 클라우드 기반 빅데이터 플랫폼 개발, 지수영
Semantic segmentation is performed to understand an image at the pixel level; it is widely used in the field of autonomous driving. In recent years, deep neural networks achieve good accuracy performance; however, there exist few models that have a good trade-off between high accuracy and low inference time. In this paper, we propose a fast spatial feature network (FSFNet), an optimized lightweight semantic segmentation model using an accelerator, offering high performance as well as faster inference speed than current methods. FSFNet employs the FSF and MRA modules. The FSF module has three different types of subset modules to extract spatial features efficiently. They are designed in consideration of the size of the spatial domain. The multi-resolution aggregation module combines features that are extracted at different resolutions to reconstruct the segmentation image accurately. Our approach is able to run at over 203 FPS at full resolution (1024 × 2048) in a single NVIDIA 1080Ti GPU, and obtains a result of 69.13% mIoU on the Cityscapes test dataset. Compared with existing models in real-time semantic segmentation, our proposed model retains remarkable accuracy while having high FPS that is over 30% faster than the state-of-the-art model. The experimental results proved that our model is an ideal approach for the Cityscapes dataset. The code is publicly available at:
Cityscapes dataset, Computer architecture, Convolution, convolutional neural network, Feature extraction, Graphics processing units, high-resolution, Image segmentation, Real-time, Real-time systems, semantic segmentation, Semantics
KSP 제안 키워드
Accuracy performance, Computer Architecture, Convolution neural network(CNN), Deep neural network(DNN), Feature extractioN, Graphic Processing Unit(GPU), High accuracy, High performance, High-resolution, Multi-resolution, Proposed model