Pith. sign in

REVIEW

Estimating and Maximizing Mutual Information for Knowledge Distillation

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2110.15946 v3 pith:DYVSR5ME submitted 2021-10-29 cs.CV cs.ITmath.IT

Estimating and Maximizing Mutual Information for Knowledge Distillation

classification cs.CV cs.ITmath.IT
keywords knowledgenetworkaccuracyinformationmodelsmutualstudentarbitrary
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

In this work, we propose Mutual Information Maximization Knowledge Distillation (MIMKD). Our method uses a contrastive objective to simultaneously estimate and maximize a lower bound on the mutual information of local and global feature representations between a teacher and a student network. We demonstrate through extensive experiments that this can be used to improve the performance of low capacity models by transferring knowledge from more performant but computationally expensive models. This can be used to produce better models that can be run on devices with low computational resources. Our method is flexible, we can distill knowledge from teachers with arbitrary network architectures to arbitrary student networks. Our empirical results show that MIMKD outperforms competing approaches across a wide range of student-teacher pairs with different capacities, with different architectures, and when student networks are with extremely low capacity. We are able to obtain 74.55% accuracy on CIFAR100 with a ShufflenetV2 from a baseline accuracy of 69.8% by distilling knowledge from ResNet-50. On Imagenet we improve a ResNet-18 network from 68.88% to 70.32% accuracy (1.44%+) using a ResNet-34 teacher network.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.