.png){kind=icon}
返回
EmbedFormer: Embedded Depth-Wise Convolution Layer for Token Mixing
.png){kind=icon}
OA
AI
DOI：10.3390/s22249854.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Visual Transformers (ViTs) have shown impressive performance due to their powerful coding ability to catch spatial and channel information. MetaFormer gives us a general architecture of transformers consisting of a token mixer and a channel mixer through which we can generally understand how transformers work. It is proved that the general architecture of the ViTs is more essential to the models' performance than self-attention mechanism. Then, Depth-wise Convolution layer (DwConv) is widely accepted to replace local self-attention in transformers. In this work, a pure convolutional transformer is designed. We rethink the difference between the operation of self-attention and DwConv. It is found that the self-attention layer, with an embedding layer, unavoidably affects channel information, while DwConv only mixes the token information per channel. To address the differences between DwConv and self-attention, we implement DwConv with an embedding layer before as the token mixer to instantiate a MetaFormer block and a model named EmbedFormer is introduced. Meanwhile, SEBlock is applied in the channel mixer part to improve performance. On the ImageNet-1K classification task, EmbedFormer achieves top-1 accuracy of 81.7% without additional training images, surpassing the Swin transformer by +0.4% in similar complexity. In addition, EmbedFormer is evaluated in downstream tasks and the results are entirely above those of PoolFormer, ResNet and DeiT. Compared with PoolFormer-S24, another instance of MetaFormer, our EmbedFormer improves the score by +3.0% box AP/+2.3% mask AP on the COCO dataset and +1.3% mIoU on the ADE20K.
Keyword:
deep learning
computer vision
CNN
vision transformer
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
3.5
论文数:
7.2W
被引数:
20.9W
机构
引用论文
Conductivity Enhancement in Thin Silicon-on-Insulator Layer Embedding Artificial Dislocation Network
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
Single-Shot Object Detection via Feature Enhancement and Channel Attention通过特征增强和通道注意力进行单次目标检测.png)
SENSORSOAAI
SENSORSIF3.5
OAAI分享收藏Synthesis of n-type semiconducting diamond film using diphosphorus pentaoxide as the doping source以五氧化二磷为掺杂源合成n型半导体金刚石膜
PREAI
分享收藏
查看更多内容