Papers › Curriculum Temperature for Knowledge Distillation

Curriculum Temperature for Knowledge Distillation

29 Nov 2022arXiv:2211.16231archive 2025-07-28

Zheng Li, Xiang Li, Lingfeng Yang, Borui Zhao, RenJie Song, Lei Luo, Jun Li, Jian Yang

Most existing distillation methods ignore the flexible role of the temperature in the loss function and fix it as a hyper-parameter that can be decided by an inefficient grid search. In general, the temperature controls the discrepancy between two distributions and can faithfully determine the difficulty level of the distillation task. Keeping a constant temperature, i.e., a fixed level of task difficulty, is usually sub-optimal for a growing student during its progressive learning stages. In this paper, we propose a simple curriculum-based technique, termed Curriculum Temperature for Knowledge Distillation (CTKD), which controls the task difficulty level during the student's learning career through a dynamic and learnable temperature. Specifically, following an easy-to-hard curriculum, we gradually increase the distillation loss w.r.t. the temperature, leading to increased distillation difficulty in an adversarial manner. As an easy-to-use plug-in technique, CTKD can be seamlessly integrated into existing knowledge distillation frameworks and brings general improvements at a negligible additional computation cost. Extensive experiments on CIFAR-100, ImageNet-2012, and MS-COCO demonstrate the effectiveness of our method. Our code is available at https://github.com/zhengli97/CTKD.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also 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

Syntology 15 code samples harvested from 1 repository linked to this paper: 8 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 7 where Syntology's instrument failed) · 7 unverified. Where Syntology's instrument failed: 7 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 15 samples from 1 repository, 8 ran (1 with no instrument failure; 7 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 3 of the 8 samples that ran have no recorded date.

zhengli97/ctkd officialmentioned in papermentioned on GitHubpytorchApache-2.0Syntology: 15 samples, 8 ran (7 instrument-failed) · 7 unverified 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.

Code Syntology ran Syntology

15 samples harvested: 8 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 7 where Syntology's instrument failed) · 7 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

7ran · our draft was wrong
1ran
7unverified

Licence: 2 of the 15 samples are pointer only, meaning Syntology does not serve that copy's text. For 2 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from zhengli97/ctkd. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

zhengli97/ctkd official repository 15 samples, 8 ran (7 instrument-failed) · 7 unverified
channel_shuffle in 35 papers
census: 3 implementations from 7 papers, 2 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 4, kind float, dtype float32
models/ShuffleNetv2_Imagenet.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) here; the stored copy is pointer only · b9da06d4f527dd6c · report fixture: signature x:Tensor/4/float, groups:int/0/int · returned Tensor · level recorded 2026-09-22
conv1x1 in 691 papers models/resnetv2.py ran · our draft was wrong Apache-2.0 (permissive) · d9def42110729a85 · report fixture: signature in_planes:int/0/int, out_planes:int/0/int, stride:int/0/int · returned Conv2d · level recorded, date not recorded
conv3x3 in 1,376 papers models/resnetv2.py ran · our draft was wrong Apache-2.0 (permissive) · 160bb14bd76201b4 · report fixture: signature in_planes:int/0/int, out_planes:int/0/int, stride:int/0/int, groups:int/0/int, dilation:int/0/int · returned Conv2d · level recorded, date not recorded
conv3x3 in 1,376 papers models/resnet.py ran · our draft was wrong Apache-2.0 (permissive) here; the stored copy is pointer only · fac5364e2f53c6db · report fixture: signature in_planes:int/0/int, out_planes:int/0/int, stride:int/0/int · returned Conv2d · level recorded, date not recorded
conv_1x1_bn in 59 papers models/mobilenetv2.py ran · our draft was wrong Apache-2.0 (permissive) · 7765583b9e540679 · report fixture: signature inp:int/0/int, oup:int/0/int · returned Sequential · level recorded 2026-09-24
conv_bn in 88 papers models/mobilenetv2.py ran · our draft was wrong Apache-2.0 (permissive) · 2f7853ff01cbbc29 · report fixture: signature inp:int/0/int, oup:int/0/int, stride:int/0/int · returned Sequential · level recorded 2026-09-22
mobilenet_v2 in 23 papers models/mobilenetv2_imagenet.py ran Apache-2.0 (permissive) · ee9a05c9ee4702a2 · report fixture: signature num_classes:int/0/int, width_mult:float/0/float, inverted_residual_setting:NoneType/0/?, round_nearest:int/0/int, block:NoneType/0/?, norm_layer:NoneType/0/? · returned MobileNetV2 · level recorded 2026-09-25
mobilenetv2_T_w in 7 papers models/mobilenetv2.py ran · our draft was wrong Apache-2.0 (permissive) · 421fd14c036bc279 · report fixture: signature T:int/0/int, W:float/0/float, feature_dim:int/0/int · returned MobileNetV2 · level recorded 2026-09-24
gap_loss models/resnet.py unverified Apache-2.0 (permissive) · fa5e65eaf182f037 · report
get_data_folder dataset/imagenet.py unverified Apache-2.0 (permissive) · 9b69431119e6f00b · report
get_imagenet_dataloader in 5 papers dataset/imagenet.py unverified Apache-2.0 (permissive) · 94fb66ad6f5924e1 · report
get_test_loader in 10 papers dataset/imagenet.py unverified Apache-2.0 (permissive) · ad816eb6904c00e3 · report
resnet18 in 432 papers models/resnetv2.py unverified Apache-2.0 (permissive) · 978acca4eb9c1fc9 · report
shufflenet_v2_x0_5 models/ShuffleNetv2_Imagenet.py unverified Apache-2.0 (permissive) · 916d6b0fde048401 · report
shufflenet_v2_x1_0 models/ShuffleNetv2_Imagenet.py unverified Apache-2.0 (permissive) · c6134299daf274a3 · report

Tasks

Image ClassificationKnowledge Distillation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Knowledge 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