Steerable Transformers
CoRR(2024)
摘要
In this work we introduce Steerable Transformers, an extension of the Vision
Transformer mechanism that maintains equivariance to the special Euclidean
group SE(d). We propose an equivariant attention mechanism that
operates on features extracted by steerable convolutions. Operating in Fourier
space, our network utilizes Fourier space non-linearities. Our experiments in
both two and three dimensions show that adding a steerable transformer encoder
layer to a steerable convolution network enhances performance.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要