Browse › Computer Vision › Semi-Supervised Image Classification › ImageNet - 1% labeled data

Semi-Supervised Image Classification archive 2025-07-28

ImageNet - 1% labeled data Benchmark (Semi-Supervised Image Classification)

65 rows 59 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; 64 of 65 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) 84.6% – Paper Code 2025 linked, not harvested report
2 REACT (ViT-Large) 81.6% ✓ 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
3 DHO (ViT-Base) 81.6% – Paper Code 2025 linked, not harvested report
4 Meta Co-Training 80.7% – 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
5 Semi-SST (ViT-Huge) 80.7% – Paper – 2025 no code linked report
6 Super-SST (ViT-Huge) 80.3% – Paper – 2025 no code linked report
7 Semi-ViT (ViT-Huge) 80%93.1 – Paper Code 2022 linked, not harvested report
8 Semi-ViT (ViT-Large) 77.3% – Paper Code 2022 linked, not harvested report
9 Super-SST (ViT-Small distilled) 76.9% – Paper – 2025 no code linked report
10 SimCLRv2 self-distilled (ResNet-152 x3, SK) 76.6%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
11 SimCLRv2 distilled (ResNet-50 x2, SK) 75.9%93.0% – 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 MSN (ViT-B/4) 75.7% – Paper Code 2022 community repositories only · 4 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; 3 where Syntology's instrument failed) · 0 unverified report
13 SimCLRv2 (ResNet-152 x3, SK) 74.9%92.3% – 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
14 SimCLRv2 distilled (ResNet-50) 73.9%91.5% – 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
15 SimMatchV2 (ResNet-50) 71.9% – Paper Code 2023 linked, not harvested report
16 Semi-SST (ViT-Small) 71.4% – Paper – 2025 no code linked report
17 DebiasPL (ResNet-50) 71.3% – Paper Code 2022 official (archive's flag): 1 ran · 1 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; 1 where Syntology's instrument failed) · 0 unverified report
18 BYOL (ResNet-200 x2) 71.2%89.5% – Paper Code 2020 official: no sample here; runs from other or unrecorded repositories · 62 ran (of which 19 constructed an object rather than computing a result; 42 with no instrument failure: 4 honoured, 1 violated, 37 with no contract checked; 20 where Syntology's instrument failed) · 17 unverified report
19 Semi-ViT (ViT-Base) 71% – Paper Code 2022 linked, not harvested report
20 Super-SST (ViT-Small) 70.4% – Paper – 2025 no code linked report
21 PAWS (ResNet-50 4x) 69.9% – 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
22 PAWS (ResNet-50 2x) 69.6% – 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
23 BYOL (ResNet-50 x4) 69.1%87.9% – Paper Code 2020 official: no sample here; runs from other or unrecorded repositories · 62 ran (of which 19 constructed an object rather than computing a result; 42 with no instrument failure: 4 honoured, 1 violated, 37 with no contract checked; 20 where Syntology's instrument failed) · 17 unverified report
24 SimMatch + EPASS (ResNet-50) 68.6%87.6 – Paper Code 2023 linked, not harvested report
25 CoMatch + EPASS (ResNet-50) 67.4%87.3 – Paper Code 2023 linked, not harvested report
26 TWIST (ResNet-50 x2) 67.2%88.2% – 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 (ResNet-50) 67.2% – Paper Code 2022 linked, not harvested report
28 CoMatch (w. MoCo v2) 67.1%87.1% – 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
29 PAWS (ResNet-50) 66.5% – 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
30 SimCLRv2 (ResNet-50 ×2) 66.3%87.4% – 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
31 WCL (ResNet-50) 65.0%86.3% – Paper Code 2021 official: harvested, nothing ran · 0 ran · 3 unverified report
32 FNC (ResNet-50) 63.7%85.3% – Paper Code 2020 linked, not harvested report
33 SimCLR (ResNet-50 4×) 63.0%85.8% – 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
34 FixMatch-EMAN 63% – Paper Code 2021 linked, not harvested report
35 SEER (RegNet10B) 62.4% – Paper Code 2022 linked, not harvested report
36 BYOL (ResNet-50 x2) 62.2%84.1% – Paper Code 2020 official: no sample here; runs from other or unrecorded repositories · 62 ran (of which 19 constructed an object rather than computing a result; 42 with no instrument failure: 4 honoured, 1 violated, 37 with no contract checked; 20 where Syntology's instrument failed) · 17 unverified report
37 iBOT (ViT-S/16) 61.9% – Paper Code 2021 official: harvested, nothing ran · 0 ran · 1 unverified report
38 SEER Large (RegNetY-256GF) 60.5% – Paper Code 2021 linked, not harvested report
39 SemiReward 59.64% – Paper Code 2023 official (archive's flag): 4 ran · 4 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified report
40 SimCLR (ResNet-50 2×) 58.5%83.0% – 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
41 RELICv2 58.1%81.3 – 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
42 SimCLRv2 (ResNet-50) 57.9%82.5% – 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
43 SEER Small (RegNetY-128GF) 57.5% – Paper Code 2021 linked, not harvested report
44 NNCLR (ResNet-50) 56.4%80.7 – 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
45 I-VNE+ (ResNet-50) 55.881.0 – Paper Code 2023 linked, not harvested report
46 Barlow Twins (ResNet-50) 55%79.2 – 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
47 VICREG (Resnet-50) 54.8%79.4% – Paper Code 2021 official (archive's flag): 4 ran · 15 ran (of which 3 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 1 violated, 8 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified report
48 SwAV (ResNet-50) 53.9%78.5 – Paper Code 2020 community repositories only · 13 ran (of which 4 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 1 violated, 4 with no contract checked; 7 where Syntology's instrument failed) · 4 unverified report
49 BYOL (ResNet-50) 53.2%78.4% – Paper Code 2020 official: no sample here; runs from other or unrecorded repositories · 62 ran (of which 19 constructed an object rather than computing a result; 42 with no instrument failure: 4 honoured, 1 violated, 37 with no contract checked; 20 where Syntology's instrument failed) · 17 unverified report
50 CPC v2 (ResNet-161) 52.7%77.9% – – – not matched report
51 SynCo (ResNet-50) 800ep 50.8%77.5%24M – Paper Code 2024 linked, not harvested report
52 SimCLR (ResNet-50) 48.3%75.5% – 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
53 SCAN (ResNet-50|Unsupervised) 39.90%60.0% – Paper Code 2020 linked, not harvested report
54 OBoW (ResNet-50) 82.9% – 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
55 PCL (ResNet-50) 75.6% – Paper Code 2020 official (archive's flag): 2 ran · 2 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; 1 where Syntology's instrument failed) · 3 unverified report
56 CPC 64.03% – 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
57 BigBiGAN (RevNet-50 ×4, BN+CReLU) 55.2% – 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
58 Rotation (joint training) 53.37% – 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 Pseudolabeling 51.56% – 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
60 Exemplar (joint training) 47.02% – 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
61 VAT + Entropy Minimization 46.96% – 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 Rotation 45.11% – 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 Exemplar 44.90% – 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 44.05% – 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 Instance Discrimination (ResNet-50) 39.20% – Paper Code 2018 linked, not harvested report

All 65 rows shown. 64 link to a paper page on this site; 1 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). 41 rows have a graph line, from 23 distinct papers. Rows whose paper has a sample that ran: 39 (36 with a run with no instrument failure, 3 where every run was a failure of Syntology's instrument). Papers: 21 with a sample that ran: 18 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 41 rows with a graph line, 31 have an archive-official repository: on 17 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 4 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 447 samples: 352 ran (of which 96 constructed an object rather than computing a result; 259 with no instrument failure: 13 honoured, 7 violated, 239 with no contract checked; 93 where Syntology's instrument failed) · 95 unverified. Separately, 181 of those 447 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), 57 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 1,547 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