Information Theoretic Representation Distillation
Roy V Miles (Imperial College London),* Adrian Lopez (Imperial College London), Krystian Mikolajczyk (Imperial College London)
The 33rd British Machine Vision Conference
Abstract
Despite the empirical success of knowledge distillation, current state-of-the-art methods are computationally expensive to train, which makes them difficult to adopt in practice. To address this problem, we introduce two distinct complementary losses inspired by a cheap entropy-like estimator. These losses aim to maximise the correlation and mutual information between the student and teacher representations. Our method incurs significantly less training overheads than other approaches and achieves competitive performance to state-of-the-art on the knowledge distillation and cross-model transfer tasks. We further demonstrate the effectiveness of our method on a binary distillation task, whereby it leads to a new state-of-the-art for binary quantisation and approaches the performance of a full precision model. Code: github.com/roymiles/ITRDVideo
Citation
@inproceedings{Miles_2022_BMVC,
author = {Roy V Miles and Adrian Lopez and Krystian Mikolajczyk},
title = {Information Theoretic Representation Distillation},
booktitle = {33rd British Machine Vision Conference 2022, {BMVC} 2022, London, UK, November 21-24, 2022},
publisher = {{BMVA} Press},
year = {2022},
url = {https://bmvc2022.mpi-inf.mpg.de/0385.pdf}
}
Copyright © 2022
The British Machine Vision Conference is organised by