Pith. sign in

REVIEW 1 cited by

Reducing the Teacher-Student Gap via Spherical Knowledge Disitllation

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 2010.07485 v5 pith:5MLCZ44G submitted 2020-10-15 cs.LG cs.CV

Reducing the Teacher-Student Gap via Spherical Knowledge Disitllation

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

Knowledge distillation aims at obtaining a compact and effective model by learning the mapping function from a much larger one. Due to the limited capacity of the student, the student would underfit the teacher. Therefore, student performance would unexpectedly drop when distilling from an oversized teacher, termed the capacity gap problem. We investigate this problem by study the gap of confidence between teacher and student. We find that the magnitude of confidence is not necessary for knowledge distillation and could harm the student performance if the student are forced to learn confidence. We propose Spherical Knowledge Distillation to eliminate this gap explicitly, which eases the underfitting problem. We find this novel knowledge representation can improve compact models with much larger teachers and is robust to temperature. We conducted experiments on both CIFAR100 and ImageNet, and achieve significant improvement. Specifically, we train ResNet18 to 73.0 accuracy, which is a substantial improvement over previous SOTA and is on par with resnet34 almost twice the student size. The implementation has been shared at https://github.com/forjiuzhou/Spherical-Knowledge-Distillation.

discussion (0)

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

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. LEAP: Layer-skipping Efficiency via Adaptive Progression for Vision Transformer Distillation

    cs.CV 2026-06 unverdicted novelty 5.0

    LEAP is an adaptive layer-skipping curriculum for ViT feature distillation that reports accuracy gains on ImageNet and retrieval tasks plus training compute savings.