.png){kind=icon}
返回
Spatial-Enhanced Multi-Level Wavelet Patching in Vision Transformers
.png){kind=icon}
OA
AI
DOI：10.1109/LSP.2024.3350811.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
By seamlessly integrating wavelet transforms into the image patching stage of ViT, we leverage the power of multi-level wavelet transforms to decompose images into a diverse array of frequency-domain features. These features, integrated with spatial characteristics at equivalent scales, enrich image details, enhancing ViT's proficiency in delineating intricate textures and distinct edges. Consequently, we registered a notable 2.7% accuracy enhancement on the ImageNet100 dataset in ViT. Our wavelet patching module, designed for versatility, seamlessly fits into various ViT derivatives without necessitating architecture modifications. This advancement has uplifted the performance of several leading vision transformers by 0.46-4.3%, preserving parameter efficiency without notable FLOPs increment.
Keyword:
Wavelet domain
Transformers
Frequency-domain analysis
Discrete wavelet transforms
Convolution
Standards
Image color analysis
Vision transformer
image patching
wavelet transform
low-level feature
期刊
IF:
9.6
论文数:
1.1W
被引数:
1.7W
机构
引用论文
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
.png){kind=icon}
PREAI
分享收藏Types of Parent Verbal Responsiveness That Predict Language in Young Children With Autism Spectrum Disorder预测自闭症谱系障碍幼儿语言的父母言语反应类型
OAAI
OAAI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
查看更多内容