Search Results for author:
Found 2 papers, 1 papers with code
Making Vision Transformers Truly Shift-Equivariant
For computer vision, Vision Transformers (ViTs) have become one of the go-to deep net architectures.
Learnable Polyphase Sampling for Shift Invariant and Equivariant Convolutional Networks
We propose learnable polyphase sampling (LPS), a pair of learnable down/upsampling layers that enable truly shift-invariant and equivariant convolutional networks.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
