Browse State-of-the-Art › Knowledge Distillation

Knowledge Distillation

1,740 papers with code · 7 benchmarks · 6 datasets archive 2025-07-28

Computer VisionNatural Language Processing

Knowledge distillation is the process of transferring knowledge from a large model to a smaller one. While large models (such as very deep neural networks or ensembles of many models) have higher knowledge capacity than small models, this capacity might not be fully utilized.

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

11 leaderboard tables shown for this task, 7 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted. 10 shown of 11 until expanded.

Syntology 2 newer papers were judged to report on this task's benchmarks so far (Claude Sonnet 4.5, reading their tables: a model's judgement, not a result; 0 placed): ImageNet (1 judged, 0 placed), CIFAR-100 (1 judged, 0 placed), PASCAL VOC (1 judged, 0 placed). Drawn from 8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read).

DatasetBest model (first row in archive order)PaperCodeSyntologyCompare
ImageNet (52 rows) ScaleKD (T:BEiT-L S:ViT-B/14) ScaleKD: Strong Vision Transformers Could Be Excellent Teachers code — Compare
CIFAR-100 (27 rows) SRD (T:resnet-32x4, S:shufflenet-v2) Understanding the Role of the Projector in Knowledge Distillation code — Compare
COCO (Common Objects in Context) (4 rows) ADLIK-Faster (T: Faster R-CNN vit-base S: Faster R-CNN deit-small) Focal and Global Knowledge Distillation for Detectors code — Compare
COCO 2017 val (3 rows) ReviewKD++(T: faster rcnn(resnet101), S:faster rcnn(resnet50)) Improving Knowledge Distillation via Regularizing Feature Norm and... code Syntology official (archive's flag): 3 ran · 3 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; 2 where Syntology's instrument failed) · 0 unverified Compare
PASCAL VOC (2 rows) LSHFM (T: ResNet101 S: ResNet50) Distilling Knowledge by Mimicking Features code Syntology official (archive's flag): 3 ran · 5 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; 4 where Syntology's instrument failed) · 1 unverified Compare
Cityscapes (1 row) CAST CAST: Contrastive Adaptation and Distillation for Semi-Supervised... — — Compare
KITTI (1 row) TIE-KD (T: Adabins S: MobileNetV2) TIE-KD: Teacher-Independent and Explainable Knowledge Distillation... code — Compare
big content (0 rows) no rows in the archive — —
en es (0 rows) no rows in the archive — —
en pt br (0 rows) no rows in the archive — —
small content (0 rows) no rows in the archive — —

Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. Each line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the row's paper, the line starts with that repository's state (“official” is the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from. A dash means no Syntology record for that paper, not a recorded non-run. Each “ran” line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

6 datasets whose archive record lists this task, ordered by the archive's paper count.

Subtasks archive 2025-07-28

2 subtasks in the archive's task tree.

Papers archive 2025-07-28

archive papers tagged: 4,240 · with a code link: 1,740 · where Syntology ran a sample: 451 (365 with a run with no instrument failure, 86 where every run was a failure of Syntology's instrument) Syntology

Show: all tagged papersonly where code ran (451 of 4,240 tagged: 365 with a run with no instrument failure, 86 where every run was a failure of Syntology's instrument)

Page 1 of 43: papers 1 to 100 of 4,240, in archive order: by repositories listed in the archive (most first), then newest first, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers that list no repository come after every paper that lists one.

Papers without a page here are shown as plain text. A Syntology line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code); hover it for the repositories the samples that ran came from. The first sentence of the abstract is shown for the first 30 papers; every abstract is on its paper's page.

Syntology lines on 58 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced; each line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.

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