.png){kind=icon}
返回
Deformable attention-oriented feature pyramid network for semantic segmentation
.png){kind=icon}
PRE
AI
DOI：10.1016/j.knosys.2022.109623.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
In the field of computer vision, the use of pyramid features can significantly improve network performance. However, the misalignment of semantic information and the scale limitation of small-scale features lead to an imbalance of feature contributions, which severely limits the performance of the feature pyramid network. In order to solve the problem of model efficiency decline caused by feature contribution imbalance, in this paper, we propose a deformable attention-oriented feature pyramid network (DAFPN). Unlike previous models, which focus solely on the semantic information between features, DAFPN uses the deformable attention mechanism to model the relationship between multiple features and then merges them in the pyramid feature fusion process. Based on DAFPN, we further propose a fully transformer-based semantic segmentation head, which achieves high performance and good scalability. Comparisons on multiple backbones reveal that our proposed model outperforms the baseline model. Under the same conditions, our method can improve the mIoU by 1 & SIM;4%, which is higher than the baseline semantic segmentation model.(C) 2022 Elsevier B.V. All rights reserved.
Keyword:
Semantic segmentation
Feature fusion
Self-attention
期刊
K
IF:
7.6
论文数:
1.3W
被引数:
4.5W
机构
引用论文
Recent Development of Dual-Dictionary Learning Approach in Medical Image Analysis and Reconstruction
OAAI
OAAI分享收藏Electrochemically assisted micro localized grafting of aptamers in a microchannel engraved in fluorinated thermoplastic polymer Dyneon THV.png)
RSC Advances
RSC AdvancesIF0
PREAI
分享收藏Facial Landmark Detection via Attention-Adaptive Deep Network基于注意力自适应深度网络的人脸特征点检测IEEE ACCESSOAAI
IEEE ACCESSIF3.6
OAAI分享收藏Aberrant PTPRO methylation in tumor tissues as a potential biomarker that predicts clinical outcomes in breast cancer patients肿瘤组织中异常的PTPRO甲基化作为预测乳腺癌患者临床结果的潜在生物标志物BMC GeneticsOAAI
BMC GeneticsIF0
OAAI分享收藏A Data-Driven Approach for Collision Risk Early Warning in Vessel Encounter Situations Using Attention-BiLSTMIEEE ACCESSOAAI
IEEE ACCESSIF3.6
OAAI分享收藏Information aggregation and fusion in deep neural networks for object interaction exploration for semantic segmentation用于语义分割的对象交互探索的深度神经网络中的信息聚合和融合
PREAI
分享收藏
查看更多内容