Boundary Enhanced Network for Improved Semantic Segmentation

Zhuang, Chengyuan; Yuan, Xiaohui; Wang, Wencheng

doi:10.1007/978-981-33-4601-7_18

Cited by 5 publications

(2 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Finally, a separate re-segmentation subnetwork is built to refine the edge-guided segmentation results. Some works regard edge detection as an auxiliary task for semantic segmentation [46][47][48]. They use an auxiliary branch network for edge detection and an explicit edge loss to supervise model training.…”

Section: Edge Extractionmentioning

confidence: 99%

See 1 more Smart Citation

Multi-Branch Adaptive Hard Region Mining Network for Urban Scene Parsing of High-Resolution Remote-Sensing Images

Bai

Cheng

et al. 2022

Remote Sensing

View full text Add to dashboard Cite

Scene parsing of high-resolution remote-sensing images (HRRSIs) refers to parsing different semantic regions from the images, which is an important fundamental task in image understanding. However, due to the inherent complexity of urban scenes, HRRSIs contain numerous object classes. These objects present large-scale variation and irregular morphological structures. Furthermore, their spatial distribution is uneven and contains substantial spatial details. All these features make it difficult to parse urban scenes accurately. To deal with these dilemmas, in this paper, we propose a multi-branch adaptive hard region mining network (MBANet) for urban scene parsing of HRRSIs. MBANet consists of three branches, namely, a multi-scale semantic branch, an adaptive hard region mining (AHRM) branch, and an edge branch. First, the multi-scale semantic branch is constructed based on a feature pyramid network (FPN). To reduce the memory footprint, ResNet50 is chosen as the backbone, which, combined with the atrous spatial pyramid pooling module, can extract rich multi-scale contextual information effectively, thereby enhancing object representation at various scales. Second, an AHRM branch is proposed to enhance feature representation of hard regions with a complex distribution, which would be difficult to parse otherwise. Third, the edge-extraction branch is introduced to supervise boundary perception training so that the contours of objects can be better captured. In our experiments, the three branches complemented each other in feature extraction and demonstrated state-of-the-art performance for urban scene parsing of HRRSIs. We also performed ablation studies on two HRRSI datasets from ISPRS and compared them with other methods.

show abstract

Section: Edge Extractionmentioning

confidence: 99%

“…Among them, ref. [47,48] both designed edge-extraction structures for encoder and decoder to enhance their boundary information. Another work [49] treats edge detection as postprocessing for semantic segmentation.…”

Section: Edge Extractionmentioning

confidence: 99%