Skip to content
conftrace_

cross attention projector

1 paper

Explore in graph

Co-occurring keywords · papers mentioning both

teacher parameter perception (1) feature mimicking (1) student backbone (1) model scaling (1) convolutional neural network (1) knowledge distillation (1) vision transformer (1) feature alignment (1) model compression (1)

Papers

ScaleKD: Strong Vision Transformers Could Be Excellent Teachers NeurIPS 2024