SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1612.03928 · 2016

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

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 1 functions out of this paper's own repositories and ran 1 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
szagoruyko/attention-transfer canonical 1 of 1
FunctionStatusWhere it lives
define_teacher Ran szagoruyko/attention-transfer/imagenet.py
pointer only (licence: NONE) · get_code("c89b4b7d35ce8ba0")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

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

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("1612.03928")
get_code_for_paper("1612.03928")
have("1612.03928")

Connect an agent — have() is free.