JC Liang, Y Cui, Q Wang, T Geng, W Wang… - arXiv preprint arXiv …, 2023 - arxiv.org
This paper presents CLUSTERFORMER, a universal vision model that is based on the CLUSTERing paradigm with TransFORMER. It comprises two novel designs: 1. recurrent …
JC Liang, Y Cui, Q Wang, T Geng, W Wang… - arXiv e …, 2023 - ui.adsabs.harvard.edu
This paper presents CLUSTERFORMER, a universal vision model that is based on the CLUSTERing paradigm with TransFORMER. It comprises two novel designs: 1. recurrent …
JC Liang, Y Cui, Q Wang, T Geng… - … seventh Conference on …, 2023 - openreview.net
This paper presents ClusterFormer, a universal vision model that is based on the Clustering paradigm with TransFormer. It comprises two novel designs: 1) recurrent cross-attention …