Improved-Flow Warp Module for Remote Sensing Semantic Segmentation
This work addresses feature misalignment in remote sensing segmentation, which is an incremental improvement for applications like aerial image analysis.
The authors tackled the problem of misaligned multi-scale features in remote sensing semantic segmentation by proposing an improved-flow warp module (IFWM) that computes pixel offsets learnably to adjust feature maps, resulting in improved segmentation accuracy as validated on several datasets.
Remote sensing semantic segmentation aims to assign automatically each pixel on aerial images with specific label. In this letter, we proposed a new module, called improved-flow warp module (IFWM), to adjust semantic feature maps across different scales for remote sensing semantic segmentation. The improved-flow warp module is applied along with the feature extraction process in the convolutional neural network. First, IFWM computes the offsets of pixels by a learnable way, which can alleviate the misalignment of the multi-scale features. Second, the offsets help with the low-resolution deep feature up-sampling process to improve the feature accordance, which boosts the accuracy of semantic segmentation. We validate our method on several remote sensing datasets, and the results prove the effectiveness of our method..