Browse › Computer Vision › Semi-Supervised Image Classification › ImageNet - 10% labeled data

Semi-Supervised Image Classification archive 2025-07-28

ImageNet - 10% labeled data Benchmark (Semi-Supervised Image Classification)

75 rows 69 with code listed 3 metrics Dataset page

Syntology Since the archive (Syntology): none placed; no newer paper judged to report on this board so far.

Semi-supervised image classification leverages unlabelled data as well as labelled data to increase classification performance.

You may want to read some blog posts to get an overview before reading the papers and checking the leaderboards:

The archive carries no text for this table; the description above is the archive's text for the task Semi-Supervised Image Classification. archive 2025-07-28

Over time archive 2025-07-28

Direction inferred from the metric name, not from the archive: Top 1 Accuracy (higher is better), Top 5 Accuracy (higher is better), Number of params (lower is better). Points are placed at the row's paper date, not an evaluation date; 75 of 75 rows carry one.

The chart needs JavaScript; the table below carries every value.

Results archive 2025-07-28

Archive rows end at the archive snapshot, 2025-07-28: no result published after that date is in this table. Rank is the archive's row order at that snapshot; not re-ranked here. Metric values are the archive's strings. Column headers sort the table in your browser; each row keeps its archive rank.

Paper Code Ran Syntology Report
1 DHO (ViT-Large) 85.9% – Paper Code 2025 linked, not harvested report
2 Meta Co-Training 85.8% – Paper Code 2023 official (archive's flag): 1 ran · 1 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; 0 where Syntology's instrument failed) · 0 unverified report
3 REACT (ViT-Large) 85.1% ✓ Paper Code 2023 official (archive's flag): 9 ran · 9 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 1 violated, 4 with no contract checked; 4 where Syntology's instrument failed) · 8 unverified report
4 Semi-SST (ViT-Huge) 84.9% – Paper – 2025 no code linked report
5 Super-SST (ViT-Huge) 84.8% – Paper – 2025 no code linked report
6 Semi-ViT (ViT-Huge) 84.3%96.6% – Paper Code 2022 linked, not harvested report
7 Semi-ViT (ViT-Large) 83.3% – Paper Code 2022 linked, not harvested report
8 DHO (ViT-Base) 82.8% – Paper Code 2025 linked, not harvested report
9 SimCLRv2 self-distilled (ResNet-152 x3, SK) 80.9%95.5% – Paper Code 2020 community repositories only · 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified report
10 Super-SST (ViT-Small distilled) 80.3% – Paper – 2025 no code linked report
11 SimCLRv2 distilled (ResNet-50 x2, SK) 80.2%95.0% – Paper Code 2020 community repositories only · 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified report
12 SimCLRv2 (ResNet-152 x3, SK) 80.1%95.0% – Paper Code 2020 community repositories only · 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified report
13 Semi-ViT (ViT-Base) 79.7% – Paper Code 2022 linked, not harvested report
14 PAWS (ResNet-50 4x) 79.0% – Paper Code 2021 official (archive's flag): 2 ran · 19 ran (of which 4 constructed an object rather than computing a result; 16 with no instrument failure: 0 honoured, 0 violated, 16 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified report
15 SEER (RegNet10B) 78.8% ✓ Paper Code 2022 linked, not harvested report
16 Semi-SST (ViT-Small) 78.6% – Paper – 2025 no code linked report
17 Super-SST (ViT-Small) 78.3% – Paper – 2025 no code linked report
18 SEER Large (RegNetY-256GF) 77.9% – Paper Code 2021 linked, not harvested report
19 PAWS (ResNet-50 2x) 77.8% – Paper Code 2021 official (archive's flag): 2 ran · 19 ran (of which 4 constructed an object rather than computing a result; 16 with no instrument failure: 0 honoured, 0 violated, 16 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified report
20 SimCLRv2 distilled (ResNet-50) 77.5%93.4% – Paper Code 2020 community repositories only · 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified report
21 Semi-ViT (ViT-Small) 77.1% – Paper Code 2022 linked, not harvested report
22 SEER Small (RegNetY-128GF) 76.7% – Paper Code 2021 linked, not harvested report
23 SimMatchV2 (ResNet-50) 76.2% – Paper Code 2023 linked, not harvested report
24 Semiformer (ViT-S + Conv) 75.5% – Paper Code 2021 linked, not harvested report
25 PAWS (ResNet-50) 75.5% – Paper Code 2021 official (archive's flag): 2 ran · 19 ran (of which 4 constructed an object rather than computing a result; 16 with no instrument failure: 0 honoured, 0 violated, 16 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified report
26 TWIST (ResNet-50 x2) 75.3%92.8% – Paper Code 2021 official (archive's flag): 9 ran · 9 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 2 honoured, 0 violated, 2 with no contract checked; 5 where Syntology's instrument failed) · 6 unverified report
27 SimMatch + EPASS (ResNet-50) 75.3%92.6 – Paper Code 2023 linked, not harvested report
28 SequenceMatch (ResNet-50) 75.2%91.9 – Paper Code 2023 linked, not harvested report
29 SimMatch (ResNet-50) 74.4% – Paper Code 2022 linked, not harvested report
30 CoMatch + EPASS (ResNet-50) 74.1%91.5 – Paper Code 2023 linked, not harvested report
31 FixMatch-EMAN 74% – Paper Code 2021 linked, not harvested report
32 CowMix (ResNet-152) 73.94%91.24% – Paper Code 2020 official (archive's flag): 1 ran · 1 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; 0 where Syntology's instrument failed) · 1 unverified; the one sample that ran constructed an object rather than computing a result report
33 SimCLRv2 (ResNet-50 x2) 73.9%91.9% – Paper Code 2020 community repositories only · 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified report
34 Meta Pseudo Labels (ResNet-50) 73.89%91.38% – Paper Code 2020 community repositories only · 12 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified report
35 CoMatch (w. MoCo v2) 73.7%91.4% – Paper Code 2020 official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified report
36 S4L-MOAM (ResNet-50 4×) 73.21%91.23% – Paper Code 2019 14 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified report
37 CPC v2 (ResNet-161) 73.1%91.2% – Paper Code 2019 2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified report
38 RELICv2 (ResNet-50) 72.4%91.2% – Paper Code 2022 official (archive's flag): 13 ran · 13 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified report
39 WCL (ResNet-50) 72.0%91.2% – Paper Code 2021 official: harvested, nothing ran · 0 ran · 3 unverified report
40 NNCLR (ResNet-50) 69.8%89.3 – Paper Code 2021 4 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; every one of the 4 samples that ran constructed an object rather than computing a result report
41 Barlow Twins (ResNet-50) 69.7%89.3 – Paper Code 2021 official (archive's flag): 1 ran · 21 ran (of which 6 constructed an object rather than computing a result; 15 with no instrument failure: 2 honoured, 1 violated, 12 with no contract checked; 6 where Syntology's instrument failed) · 5 unverified report
42 I-VNE+ (ResNet-50) 69.189.9 – Paper Code 2023 linked, not harvested report
43 SimCLRv2 (ResNet-50) 68.4%89.2% – Paper Code 2020 community repositories only · 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified report
44 SynCo (ResNet-50) 800ep 66.6%88.0%24M – Paper Code 2024 linked, not harvested report
45 FlexMatch 64.79%86.04% – Paper Code 2021 official (archive's flag): 2 ran · 4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified report
46 Dual Student 63.52%83.58% – Paper Code 2019 linked, not harvested report
47 NP-Match(ResNet-50) 58.22% – Paper Code 2022 official: no sample here; runs from other or unrecorded repositories · 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified report
48 SimCLR (ResNet-50 4×) 92.6% – Paper Code 2020 official (archive's flag): 2 ran · 115 ran (of which 33 constructed an object rather than computing a result; 89 with no instrument failure: 1 honoured, 1 violated, 87 with no contract checked; 26 where Syntology's instrument failed) · 22 unverified report
49 Rotation + VAT + Ent. Min. 91.23% – Paper Code 2019 14 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified report
50 SimCLR (ResNet-50 2×) 91.2% – Paper Code 2020 official (archive's flag): 2 ran · 115 ran (of which 33 constructed an object rather than computing a result; 89 with no instrument failure: 1 honoured, 1 violated, 87 with no contract checked; 26 where Syntology's instrument failed) · 22 unverified report
51 Mean Teacher (ResNeXt-152) 90.89% – Paper Code 2017 official: no sample here; runs from other or unrecorded repositories · 6 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified report
52 OBoW (ResNet-50) 90.7% – Paper Code 2020 official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified report
53 R2-D2 (ResNet-18) 90.48% – Paper Code 2019 linked, not harvested report
54 FixMatch 89.13% – Paper Code 2020 community repositories only · 53 ran (of which 13 constructed an object rather than computing a result; 25 with no instrument failure: 3 honoured, 2 violated, 20 with no contract checked; 28 where Syntology's instrument failed) · 21 unverified report
55 UDA 88.52 – Paper Code 2019 official (archive's flag): 10 ran · 30 ran (of which 3 constructed an object rather than computing a result; 22 with no instrument failure: 2 honoured, 0 violated, 20 with no contract checked; 8 where Syntology's instrument failed) · 22 unverified report
56 SimCLR (ResNet-50) 87.8% – Paper Code 2020 official (archive's flag): 2 ran · 115 ran (of which 33 constructed an object rather than computing a result; 89 with no instrument failure: 1 honoured, 1 violated, 87 with no contract checked; 26 where Syntology's instrument failed) · 22 unverified report
57 CPC 84.88% – Paper Code 2018 35 ran (of which 21 constructed an object rather than computing a result; 30 with no instrument failure: 1 honoured, 0 violated, 29 with no contract checked; 5 where Syntology's instrument failed) · 10 unverified report
58 S4L-Rotation (ResNet-50) 83.82% – Paper Code 2019 14 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified report
59 Rotation (joint training) 83.82% – Paper – 2019 no code linked report
60 PIRL (ResNet-50) 83.8% – Paper Code 2019 3 ran (of which 3 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) · 1 unverified; every one of the 3 samples that ran constructed an object rather than computing a result report
61 S4L-Exemplar (ResNet-50) 83.72% – Paper Code 2019 14 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified report
62 Exemplar (joint training) 83.72% – Paper Code 2019 14 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified report
63 VAT + Entropy Minimization (ResNet-50) 83.39% – Paper Code 2019 14 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified report
64 VAT + Entropy Minimization 83.39% – Paper Code 2019 14 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified report
65 VAT (ResNet-50) 82.78% – Paper Code 2019 14 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified report
66 VAT 82.78% – Paper Code 2019 14 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified report
67 Pseudolabeling (ResNet-50) 82.41% – Paper Code 2019 14 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified report
68 Pseudolabeling 82.41% – Paper Code 2019 14 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified report
69 Exemplar Fine-tuned (ResNet-50) 81.01% – Paper Code 2019 14 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified report
70 Exemplar 81.01% – Paper Code 2019 14 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified report
71 BigBiGAN (RevNet-50 ×4, BN+CReLU) 78.8% – Paper Code 2019 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified report
72 Rotation Fine-tuned (ResNet-50) 78.53% – Paper Code 2019 14 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified report
73 Rotation 78.53% – Paper Code 2019 14 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified report
74 Instance Discrimination 77.40% – Paper Code 2018 linked, not harvested report
75 InstDisc (ResNet-50) 77.4% – Paper Code 2018 linked, not harvested report

All 75 rows shown. 75 link to a paper page on this site; 2 are marked as using additional training data in the archive. No GitHub stars are tracked; "Code" is the first repository the archive lists for the row. The archive carries no row tags, review links or community-submitted rows for this table; none are shown. archive 2025-07-28

Syntology Ran 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”: of the code samples Syntology harvested from repositories linked to that row's paper (joined by arXiv id), N executed on a synthesized input and U are unverified (harvested, no recorded run). Of the N, C constructed an object rather than computing a result (a part of N, never taken away from it), K ran with no instrument failure (honoured or violated the contract Syntology drafted, or ran with no contract checked) and I are failures of Syntology's instrument, not of the code (a wrong contract draft, or a contract check that could not run). It counts code from repositories linked to that row's paper, not this result: the row's number was not reproduced and nothing here is a correctness claim. The other cell texts mean no graph line for the row: "linked, not harvested" (the archive links code, Syntology has not harvested it), "no code linked" (no code link in the archive), "not matched" (the row's paper URL matched no paper on this site). 47 rows have a graph line, from 24 distinct papers. Rows whose paper has a sample that ran: 46 (43 with a run with no instrument failure, 3 where every run was a failure of Syntology's instrument). Papers: 23 with a sample that ran: 20 with a run with no instrument failure, 3 where every run was a failure of Syntology's instrument. Whose code ran. When the archive marks a repository official for the row's paper, the cell starts with that repository's state (“official” is the archive's flag, not a verdict on who wrote the code): “official (archive's flag): N ran” counts the samples from it that ran, instrument failures included; “official: harvested, nothing ran”; when it has no sample for this paper and other samples ran, “community repositories only” if every one came from a repository the archive lists for the paper but neither marks official nor records as mentioned in it, or one Syntology harvested outside the archive's links, and “official: no sample here; runs from other or unrecorded repositories” if any came from a repository named in the paper or found in its text by Syntology, or has no repository recorded; “official: harvested for another paper” (no sample from it is linked to this paper) or “official: not harvested”. No state is printed when the archive marks none official. The cell's tooltip names the repositories the samples that ran came from. Of the 47 rows with a graph line, 27 have an archive-official repository: on 16 a sample from it ran (10 with a run with no instrument failure), on 8 the samples that ran came from community repositories only, and on 2 from other or unrecorded repositories. The filters above hide rows and never renumber them; the first two count, by default, only a run with no instrument failure, and offer any run, instrument failures included. Counting each paper once, of 479 samples: 363 ran (of which 88 constructed an object rather than computing a result; 259 with no instrument failure: 13 honoured, 7 violated, 239 with no contract checked; 104 where Syntology's instrument failed) · 116 unverified. Separately, 175 of those 479 are pointer-only (licence): the site points at that code rather than redistributing it, a licence property recorded for ran and unverified samples alike; each cell's tooltip carries the row's own pointer-only count. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. Per-sample status is on the paper page; each Ran cell links to that paper's sample list. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.

Since the archive Syntology

Of the 8,888 newer papers whose tables Syntology has read (8,886 checked in full and 2 with a leaderboard still awaiting a verdict), 62 had this board among the leaderboards the extractor considered for their tables (it keeps at most 10 boards per paper and 4 per dataset; the lists of 1,542 of the 8,888 were already full without this board, so if it was crowded out of them it is not counted), and none proposed a result, so none await a verdict and none were placed. Syntology has checked 8,886 of the 18,637 papers on this site that are newer than the archive (for 3,717 of them no archive leaderboard matched the paper's tables, so there was nothing further to check); 733 were read and have nothing to place (arXiv has no HTML version of the paper, or that version has no tables), 41 could not be read (the extractor's reply could not be parsed), and results from the other 8,977 appear after they are checked.

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