Example: barber
Training data-efficient image transformers & distillation ...

Training data-efficient image transformers & distillation ...

Back to document page

forms vanilla distillation by a significant margin. •Interestingly, with our distillation, image transformers learn more from a ... For example, Squeeze and Excitation [2], Selective Kernel [34] and Split-Attention Networks [61] exploit mechanism akin …

  Margin, Squeeze

Download Training data-efficient image transformers & distillation ...


Information

Domain:

Source:

Link to this page:

Please notify us if you found a problem with this document:

Other abuse

Advertisement

Related search queries