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.

We propose a new semantic segmentation method and the necessity of certainty for practical use of semantic segmentation in scene understanding. We implement a deep fully convolutional encoder-decoder neural network for semantic segmentation. This network architecture makes the segmentation accuracy improve by retaining boundary details in the extracted image representation. This accuracy means how much the segmentation results match to ground truth labels. However, the conventional evaluation method ignores unlabeled regions in ground truth labels. In other words, the segmentation results has not been evaluated in the regions of unknown objects. Toward practical use of the semantic segmentation, the evaluation should consider such regions. So it is necessary to recognize accurately whether the object is known or not. We call this factor certainty. Bayesian SegNet makes it possible to produce an uncertainty of the segmentation results with a measure of model uncertainty from the sampling of the posterior distribution of the model using Dropout. However, the uncertainty is not used for segmentation itself, and all pixels are classified into one of the predefined classes in this segmentation result. It means that the pixels within the regions of unknown objects are definitely misclassified as one of the predefined classes. Our study aims the improvement of certainty for semantic segmentation in road scene understanding with model uncertainty. Our method rejects the uncertain region and classifies it as an unknown object using the model uncertainty. We achieved improvement of certainty by our method as shown in the evaluation results. Furthermore, we indicated the possibility of the performance improvement on the deep convolutional encoder-decoder network architecture from the comparison of our network architecture with Bayesian SegNet architecture.