stanford-futuredata/equivariant-transformers

Equivariant Transformer (ET) layers are image-to-image mappings that incorporate prior knowledge on invariances with respect to continuous transformations groups (ICML 2019). Paper: https://arxiv.org/abs/1901.11399

语言：Jupyter Notebook · GitHub 星标：93 · Fork：9

话题：computer-vision · convolutional-neural-networks · equivariance · invariance

在 GitHub 上查看原仓库