@inproceedings{learningpatchtoclusterattentioninvision, title = {PaCa-ViT: Learning Patch-to-Cluster Attention in Vision Transformers}, author = {Ryan Grainger and Thomas Paniagua and Xi Song and Naresh Cuntoor and Mun Wai Lee and Tianfu Wu}, year = {2022}, booktitle = {CVPR 2023 1}, eprint = {2203.11987}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2203.11987v2}, }