.png){kind=icon}
返回
EfficientFusion: simple and efficient learning with pixel-level fusion for semantic segmentation
.png){kind=icon}
PRE
AI
DOI：10.1007/s00530-024-01497-4.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Semantic segmentation is a task that aims to help computers better understand images. The introduction of Vision Transformer has resulted in a shift from traditional CNN architectures to Transformer architectures for many downstream computer vision tasks, especially semantic segmentation tasks. However, the patch-based strategy in Vision Transformer still faces certain limitations. The first limitation is incoherent contextual information caused by the patch-based strategy. The second limitation is redundancy in the number of patches. To address these challenges, we propose a Pixel-Level Fusion block. This block enhances the contextual relationship between patches while merging redundant patches to reduce the overall number of patches with a similarity algorithm. On the COCO-Stuff10k[33] dataset, our method shows significant improvements compared to the state-of-the-art. Specifically, our method achieves a 19.4% increase in mIoU while also providing a 21.6% inference speed improvement on GPU.
Keyword:
Semantic segmentation
Efficient learning
Token optimization
Bipartite graph matching
期刊
IF:
3.1
论文数:
2.8K
被引数:
2.7K
机构
引用论文
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
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
查看更多内容