Papers › Knowledge distillation: A good teacher is patient and consistent

Knowledge distillation: A good teacher is patient and consistent

9 Jun 2021CVPR 2022 1arXiv:2106.05237archive 2025-07-28

Lucas Beyer, Xiaohua Zhai, Amélie Royer, Larisa Markeeva, Rohan Anil, Alexander Kolesnikov

There is a growing discrepancy in computer vision between large-scale models that achieve state-of-the-art performance and models that are affordable in practical applications. In this paper we address this issue and significantly bridge the gap between these two types of models. Throughout our empirical investigation we do not aim to necessarily propose a new method, but strive to identify a robust and effective recipe for making state-of-the-art large scale models affordable in practice. We demonstrate that, when performed correctly, knowledge distillation can be a powerful tool for reducing the size of large models without compromising their performance. In particular, we uncover that there are certain implicit design choices, which may drastically affect the effectiveness of distillation. Our key contribution is the explicit identification of these design choices, which were not previously articulated in the literature. We back up our findings by a comprehensive empirical study, demonstrate compelling results on a wide range of vision datasets and, in particular, obtain a state-of-the-art ResNet-50 model for ImageNet, which achieves 82.8% top-1 accuracy.

PaperPDFConference PDFCode

In Syntology View this paper on Syntology, its page in Syntology's graph. That page lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

google-research/big_vision officialmentioned in papermentioned on GitHubjaxSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to How to train your ViT? Data, Augmentation, and Regularization in Vision Transformers (arXiv:2106.10270; that paper's own run record: 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified), UViM: A Unified Modeling Approach for Vision with Learned Guiding Codes (arXiv:2205.10337; that paper's own run record: 2 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified), PaLI: A Jointly-Scaled Multilingual Language-Image Model (arXiv:2209.06794; that paper's own run record: 2 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified) and 4 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. report
google-research/big_transfer mentioned on GitHubjaxApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Robust and Efficient Medical Imaging with Self-Supervision (arXiv:2205.09723; that paper's own run record: 20 ran (of which 0 constructed an object rather than computing a result; 16 with no instrument failure: 0 honoured, 1 violated, 15 with no contract checked; 4 where Syntology's instrument failed) · 8 unverified); nothing checks that they implement this paper's method. report
manncodes/dehazing-openvino mentioned on GitHubpytorchSyntology: not harvested report
sayakpaul/FunMatch-Distillation mentioned on GitHubtfSyntology: not harvested report
MindSpore-scientific-2/code-10 mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Normalizing Flows are Capable Generative Models (arXiv:2412.06329; that paper's own run record: 4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
MindSpore-scientific-2/code-4 mindsporeSyntology: not harvested report
MindSpore-scientific-2/code-5 mindsporeSyntology: not harvested report
MindSpore-scientific/code-10 mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Open-Sora: Democratizing Efficient Video Production for All (arXiv:2412.20404; that paper's own run record: 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
MindSpore-scientific/code-4 mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Actions Speak Louder than Words: Trillion-Parameter Sequential Transducers for... (arXiv:2402.17152; that paper's own run record: 15 ran (of which 13 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 1 where Syntology's instrument failed) · 27 unverified); nothing checks that they implement this paper's method. report
MindSpore-scientific/code-8 mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to SimBa: Simplicity Bias for Scaling Up Parameters in Deep Reinforcement Learning (arXiv:2410.09754; that paper's own run record: 6 ran (of which 2 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Image ClassificationKnowledge Distillation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Classification ImageNet FunMatch - T384+224 (ResNet-50) Top 1 Accuracy 82.8% #493 of 1060 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Distributed ShampooKnowledge Distillation

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections