Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfer

Code

• github.com/szagoruyko/attention-transfer
  OfficialIn paperpytorch★ 0
• github.com/jiahuiiiiii/adapi
  pytorch★ 5
• github.com/AlexandrosFerles/NIPS_2019_Reproducibilty_Challenge_Zero-shot_Knowledge_Transfer_via_Adversarial_Belief_Matching
  pytorch★ 0
• github.com/Marior87/Telegram_Bot
  tf★ 0
• github.com/bharatsau/Darknet2
  none★ 0

Abstract

Attention plays a critical role in human visual experience. Furthermore, it has recently been demonstrated that attention can also play an important role in the context of applying artificial neural networks to a variety of tasks from fields such as computer vision and NLP. In this work we show that, by properly defining attention for convolutional neural networks, we can actually use this type of information in order to significantly improve the performance of a student CNN network by forcing it to mimic the attention maps of a powerful teacher network. To that end, we propose several novel methods of transferring attention, showing consistent improvement across a variety of datasets and convolutional neural network architectures. Code and models for our experiments are available at https://github.com/szagoruyko/attention-transfer

Tasks

Benchmark Results

Reproductions