Copy the Same, Distill the Difference: Initializing Linear Vision Transformers
Linear Vision Transformers (ViTs) are designed to replace the attention in Softmax ViTs with the linear-complexity attention operator for more efficient token routing, but they require from-scratch pre-training and typically underperform the original Softmax version. How to initialize linear ViTs both efficiently and e...
Huai-Yuan Qin, Mu-Li Yang, Gabriel James Goenawan et al.
· 0 citations