Context and Spatial Feature Calibration for Real-Time Semantic Segmentation

• Published in: IEEE transactions on image processing Vol. 32; pp. 5465 - 5477
• Main Authors: Li, Kaige, Geng, Qichuan, Wan, Maoxian, Cao, Xiaochun, Zhou, Zhong
• Format: Journal Article
• Language: English
• Published: New York IEEE 2023; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Aggregates; Calibration; Context; context feature calibration; Context modeling; Misalignment; Modules; Pixels; Real time; Real-time semantic segmentation; Real-time systems; Sampling; Semantic segmentation; Semantics; spatial feature calibration; Transformers

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 hinder...