Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfer
This work addresses performance enhancement in CNNs for computer vision tasks, offering an incremental method based on attention transfer.
The paper tackled the problem of improving convolutional neural network performance by transferring attention maps from a teacher network to a student network, resulting in consistent improvements across various datasets and architectures.
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