NAVE	Networked Augmented Virtual Environment (NAVE) Group

Publication:Kaige Li, Qichuan Geng, Maoxian Wan, Xiaochun Cao,  Zhong Zhou. Context and Spatial Feature Calibration for Real-Time Semantic Segmentation[J]. IEEE Transactions on Image Processing (TIP). 2023, 32:5465-5477. (CCF A Journal, IF:10.6) link pdf source         Context modeling or multi-level feature fusion methods have been proved to be effective in improving semantic segmentation performance. However, they are not specialized to deal with the problems of pixel-context mismatch and spatial feature misalignment, and the high computational complexity hinders their widespread application in real-time scenarios. In this work, we propose a lightweight Context and Spatial Feature Calibration Network (CSFCN) to address the above issues with pooling-based and sampling-based attention mechanisms. CSFCN contains two core modules: Context Feature Calibration (CFC) module and Spatial Feature Calibration (SFC) module. CFC adopts a cascaded pyramid pooling module to efficiently capture nested contexts, and then aggregates private contexts for each pixel based on pixel-context similarity to realize context feature calibration. SFC splits features into multiple groups of sub-features along the channel dimension and propagates subfeatures therein by the learnable sampling to achieve spatial feature calibration. Extensive experiments on the Cityscapes and CamVid datasets illustrate that our method achieves a stateof-the-art trade-off between speed and accuracy. Concretely, our method achieves 78.7% mIoU with 70.0 FPS and 77.8% mIoU with 179.2 FPS on the Cityscapes and CamVid test sets, respectively. The code is available at http://nave.vr3i.com/ and https://github.com/kaigelee/CSFCN. create by admin at 2023-11-02 20:26:42