.png){kind=icon}
返回
Multi-query and multi-level enhanced network for semantic segmentation
.png){kind=icon}
PRE
AI
DOI：10.1016/j.patcog.2024.110777.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Plain transformer-based methods have achieved promising performance on semantic segmentation recently. These methods adopt a single set of class queries to predict masks of different semantic categories based on multi-level feature maps. We argue that this single-query design cannot fully exploit diverse information of different levels for improved semantic segmentation. To address this issue, we propose a multi-query and multi-level enhanced network for semantic segmentation (named QLSeg). Our QLSeg first performs multilevel feature enhancement on plain transformer to improve feature discriminability. Afterwards, we introduce multi-query decoder to respectively extract feature embeddings and predict mask logits at different levels, where feature embeddings are adaptively merged for classification and mask logits are summed for output masks. In addition, we introduce masked attention-to-mask to focus on local regions with the same class. We perform the experiments on three widely-used semantic segmentation datasets: ADE20K, COCO-Stuff-10K, and PASCAL-Context. Our proposed QLSeg achieves competitive results on all these three datasets.
Keyword:
Semantic segmentation
Transformer
Multi-query
Multi-level
期刊
IF:
7.6
论文数:
1.3W
被引数:
4.5W
机构
引用论文
Cross-Modal Transformer for RGB-D semantic segmentation of production workshop objects用于生产车间对象的rgb-d语义分割的跨模态变换器.png)
PATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
分享收藏A Hybrid Fuzzy Group Multi-Criteria Assessment of Structural Solutions of the Symmetric Frame AlternativesSymmetry
OAAI
SymmetryIF0
OAAI分享收藏Thermal comfort, perceived air quality, and cognitive performance when personally controlled air movement is used by tropically acclimatized persons当热带适应的人使用个人控制的空气运动时，热舒适性，感知的空气质量和认知表现Indoor AirOAAI
Indoor AirIF0
OAAI分享收藏
Using SEPIC Topology for Improving Power Factor in Distributed Power Supply SystemsEPE Journal
EPE JournalIF0
PREAI
分享收藏
查看更多内容