SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2203.08679 · CVPR · 2022

Decoupled Knowledge Distillation

Jiajun Liang, Borui Zhao, Renjie Song, Quan Cui, Yiyu Qiu

arXiv · PDF · Open in the Atlas

Code that ran

6 of 6 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (2 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 0 violated it and 2 have no contract verdict; 3 failures of our instrument; 0 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2203.08679.json · badge: /api/ran/2203.08679.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
megvii-research/mdistiller marked official in Papers with Code
Papers with Code archive
6 ran · 0 no recorded run
FunctionStatusWhere it lives
DKD Ran
ran on a synthesized input · constructed an object; no result was computed
megvii-research/mdistiller/mdistiller/distillers/DKD.py
pointer only (licence: NONE) · get_code("ff70b2d07fb71583")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, megvii-research/mdistiller when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

Distiller Ran
ran on a synthesized input · constructed an object; no result was computed
megvii-research/mdistiller/mdistiller/distillers/DKD.py
pointer only (licence: NONE) · get_code("5102cbbc15c6cc90")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, megvii-research/mdistiller when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

_get_gt_mask Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
megvii-research/mdistiller/mdistiller/distillers/DKD.py
pointer only (licence: NONE) · get_code("c414ec11055678a1")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, megvii-research/mdistiller when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

_get_other_mask Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
megvii-research/mdistiller/mdistiller/distillers/DKD.py
pointer only (licence: NONE) · get_code("6e77e58e6d85d7e4")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, megvii-research/mdistiller when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

cat_mask Ran
ran, honoured the contract we drafted
megvii-research/mdistiller/mdistiller/distillers/DKD.py
pointer only (licence: NONE) · get_code("a05175b39afcdcfe")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, megvii-research/mdistiller when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

dkd_loss Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
megvii-research/mdistiller/mdistiller/distillers/DKD.py
pointer only (licence: NONE) · get_code("4f5a2ac497ae4e80")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, megvii-research/mdistiller when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

Also present in other papers' code

Of 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 6 distinct functions with an identity, 2 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 2 later) and 4 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
Distiller
brick of this paper's assembly: helper
3 other papers
3 later · 3 only as an assembly brick
2304.12777 (2023-04)
Class Attention Transfer Based Knowledge Distillation
2305.13948 (2023-05)
Decoupled Kullback-Leibler Divergence Loss
2502.20760 (2025-02)
VRM: Knowledge Distillation via Virtual Relation Matching
cat_mask
brick of this paper's assembly: helper
2 other papers
2 later
aaai_25216 (2023 (year only))
Disentangle and Remerge: Interventional Knowledge Distillation for Few-Shot Object Detection from a Conditional Causal Perspective
Ma_Aligning_Logits_Generatively_for_Principled_Black-Box_Knowledge_Distillation_CVPR_2024_paper (2024 (year only))
Aligning Logits Generatively for Principled Black-Box Knowledge Distillation

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

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

Abstract

State-of-the-art distillation methods are mainly based on distilling deep features from intermediate layers, while the significance of logit distillation is greatly overlooked. To provide a novel viewpoint to study logit distillation, we reformulate the classical KD loss into two parts, i.e., target class knowledge distillation (TCKD) and non-target class knowledge distillation (NCKD). We empirically investigate and prove the effects of the two parts: TCKD transfers knowledge concerning the "difficulty" of training samples, while NCKD is the prominent reason why logit distillation works. More importantly, we reveal that the classical KD loss is a coupled formulation, which (1) suppresses the effectiveness of NCKD and (2) limits the flexibility to balance these two parts. To address these issues, we present Decoupled Knowledge Distillation (DKD), enabling TCKD and NCKD to play their roles more efficiently and flexibly. Compared with complex feature-based methods, our DKD achieves comparable or even better results and has better training efficiency on CIFAR-100, ImageNet, and MS-COCO datasets for image classification and object detection tasks. This paper proves the great potential of logit distillation, and we hope it will be helpful for future research. The code is available at https://github.com/megviiresearch/mdistiller.

For agents

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

get_harvested_code_for_paper("2203.08679")
get_code_for_paper("2203.08679")
have("2203.08679")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2203.08679.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2203.08679.svg)](https://syntology.ai/paper/2203.08679)

Connect an agent — have() is free.