.png){kind=icon}
返回
LBFormer: Scene Perception Segmentation Transformer Based on Local Block
.png){kind=icon}
PRE
AI
DOI：10.1109/TII.2024.3477554.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Scene perception for autonomous vehicles and vessels is crucial for autonomous navigation. Current mainstream transformer methods typically split the feature map into windows, such as local, dilated, and horizontal/vertical bar windows. However, their token interaction is confined to fixed windows, posing challenges for image-based semantic segmentation. This article proposes a novel model, LBFormer, which enables flexible token interaction across different windows. Specifically, a window-level affinity graph is constructed from coarse-grained features using self-attention clustering and evolves during training, retaining top-k windows with high semantic relevance for each window. Self-attention purification is then employed to compress and filter fine-grained features with low semantic relevance within the top-k windows, ensuring effective token interaction for each feature point. To enhance context modeling within windows and build a more effective window-level affinity graph, a dual branch method extracts multidimensional features from each window, which are then interacted with and fused via the feature aggregation module. Extensive experiments at an image resolution of 224x224 were conducted on our private YZ-DATA water surface scene dataset and the public CamVid urban scene dataset. The results show that LBFormer achieves an MIoU of 89.80% on YZ-DATA and 61.31% on CamVid, surpassing mainstream transformer methods.
Keyword:
LBFormer
scene perception
semantic segmentation
transformer
期刊
IF:
9.9
论文数:
8.5K
被引数:
6.0W
机构
引用论文
分享收藏Molecular and Pharmacological Characterization of GABAA Receptors in the Rat Pituitary大鼠垂体中GABAA 受体的分子和药理学特征
PREAI
分享收藏Effect of viscosity on the electrical properties of conducting thermoplastic composites made by compression molding of a powder mixture粘度对通过粉末混合物的压缩成型制成的导电热塑性复合材料的电性能的影响
PREAI
分享收藏Inflexibility of mental planning: A characteristic disorder with prefrontal lobe lesions?心理计划的僵化: 前额叶病变的特征性障碍？
PREAI
分享收藏Parallel Deep Learning Algorithms With Hybrid Attention Mechanism for Image Segmentation of Lung Tumors基于混合注意力机制的并行深度学习算法在肺部肿瘤图像分割中的应用
PREAI
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Low temperature analysis of the axial next-nearest neighbour Ising model near its multiphase point
PREAI
分享收藏Classification of Diabetic Retinopathy Severity Based on GCA Attention MechanismIEEE ACCESS
OAAI
IEEE ACCESSIF3.6
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