Semantic Segmentation with Attention-Modulated Feature Fusion in HRNET V2

Semantic segmentation is pivotal for precise object identification and localization within images, a cornerstone for automated analysis and machine vision. Despite advancements, challenges persist, particularly in segmenting small objects and recognizing multi-class large objects. This paper introduces a novel approach to enhance HRNet V2 by integrating a Squeeze-and-Attention (SA) Block, which enables dynamic feature selection and integration across resolutions, leading to more accurate segmentation results. We propose three strategies: the Master Strategy focusing on output resolution features, the Slave Strategy sharing features from other resolutions, and the Dual Strategy integrating features determined by weights from two resolutions. Our experiments on the Cityscapes dataset demonstrate significant improvements, with the Dual Strategy outperforming conventional methods by 4.86pt in mIoU scores. These results underscore the potential of our approach to significantly advance semantic segmentation.