Enhanced Feature Pyramid Network for Semantic Segmentation

Ye, Mucong; Ouyang, Jingpeng; Chen, Ge; Zhang, Jing; Yu, Xiaogang

doi:10.1109/icpr48806.2021.9413224

Cited by 7 publications

(1 citation statement)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Rather than using the gating mechanism, ref. [29] introduced a semantic enhancement module in the decoder of an FPN to enhance shallow features. The method is to use an edge-extraction module to supplement deep features and utilize a context aggregation module to boost the performance of multi-feature aggregation.…”

Section: Multi-scale Feature Extractionmentioning

confidence: 99%

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: Multi-scale Feature Extractionmentioning

confidence: 99%