Using Deep Guided Decoder (DGD) networks, trained with a novel Semantic Boundary-Aware Learning (SBAL) strategy, in order to improve semantic boundary accuracy.
Image semantic segmentation is ubiquitously used in scene understanding applications, such as AI Camera, which require high accuracy and efficiency. Deep learning has significantly advanced the state-of-the-art in semantic segmentation. However, many of recent semantic segmentation works only consider class accuracy and ignore the accuracies at the boundaries between semantic classes. To improve the semantic boundary accuracy, we propose low complexity Deep Guided Decoder (DGD) networks, trained with a novel Semantic Boundary-Aware Learning (SBAL) strategy. Our ablation studies on Cityscapes and the ADE20K-32 confirm the effectiveness of our approach with network of different complexities. We show that our DeepGBASS approach significantly improves the mIoU by up to 11% relative gain and the mean boundary F1-score (mBF) by up to 39.4% when training MobileNetEdgeTPU DeepLab on ADE20K-32 dataset.
Authors: Qingfeng Liu, Hai Su, Mostafa El-Khamy, Kee-Bong Song, of SOC Multimedia R&D, Samsung Semiconductor, Inc., USA
Published in: ICASSP 2022 – 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
DOI: 10.1109/ICASSP43922.2022.9747892
Click here to read more.
 |
 |
 |
 |
 |
 |
 |  |
Leave a Reply