A newton interpolation network for smoke semantic segmentation

Open Webpage

Feiniu Yuan, Guiqian Wang, Qinghua Huang, Xuelong Li

Published: 01 Jan 2025, Last Modified: 16 Nov 2025Pattern Recognit. 2025EveryoneRevisionsBibTeXCC BY-SA 4.0
Abstract: Highlights•We propose a Newton Interpolation Module (NIM) for extracting structured information from sequential feature maps.•We repeatedly stack NIMs at different levels of decoding stages for extracting multi-scale information.•We propose to use a higher order Newton interpolation polynomial for capturing higher order information.