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

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

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

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; 75 of 75 rows carry one.

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 1 of 1 ran · 0 unverified report
3 REACT (ViT-Large) 85.1% ✓ Paper Code 2023 6 of 17 ran · 11 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 0 of 6 ran · 6 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 0 of 6 ran · 6 unverified report
12 SimCLRv2 (ResNet-152 x3, SK) 80.1%95.0% – Paper Code 2020 0 of 6 ran · 6 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 7 of 21 ran · 14 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 7 of 21 ran · 14 unverified report
20 SimCLRv2 distilled (ResNet-50) 77.5%93.4% – Paper Code 2020 0 of 6 ran · 6 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 7 of 21 ran · 14 unverified report
26 TWIST (ResNet-50 x2) 75.3%92.8% – Paper Code 2021 5 of 15 ran · 10 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 1 of 2 ran · 1 unverified report
33 SimCLRv2 (ResNet-50 x2) 73.9%91.9% – Paper Code 2020 0 of 6 ran · 6 unverified report
34 Meta Pseudo Labels (ResNet-50) 73.89%91.38% – Paper Code 2020 5 of 14 ran · 9 unverified report
35 CoMatch (w. MoCo v2) 73.7%91.4% – Paper Code 2020 2 of 3 ran · 1 unverified report
36 S4L-MOAM (ResNet-50 4×) 73.21%91.23% – Paper Code 2019 0 of 19 ran · 19 unverified report
37 CPC v2 (ResNet-161) 73.1%91.2% – Paper Code 2019 2 of 2 ran · 0 unverified report
38 RELICv2 (ResNet-50) 72.4%91.2% – Paper Code 2022 0 of 14 ran · 14 unverified report
39 WCL (ResNet-50) 72.0%91.2% – Paper Code 2021 0 of 3 ran · 3 unverified report
40 NNCLR (ResNet-50) 69.8%89.3 – Paper Code 2021 4 of 5 ran · 1 unverified report
41 Barlow Twins (ResNet-50) 69.7%89.3 – Paper Code 2021 21 of 26 ran · 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 0 of 6 ran · 6 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 4 of 6 ran · 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 1 of 1 ran · 0 unverified report
48 SimCLR (ResNet-50 4×) 92.6% – Paper Code 2020 79 of 137 ran · 58 unverified report
49 Rotation + VAT + Ent. Min. 91.23% – Paper Code 2019 0 of 19 ran · 19 unverified report
50 SimCLR (ResNet-50 2×) 91.2% – Paper Code 2020 79 of 137 ran · 58 unverified report
51 Mean Teacher (ResNeXt-152) 90.89% – Paper Code 2017 6 of 6 ran · 0 unverified report
52 OBoW (ResNet-50) 90.7% – Paper Code 2020 3 of 3 ran · 0 unverified report
53 R2-D2 (ResNet-18) 90.48% – Paper Code 2019 linked, not harvested report
54 FixMatch 89.13% – Paper Code 2020 50 of 74 ran · 24 unverified report
55 UDA 88.52 – Paper Code 2019 15 of 52 ran · 37 unverified report
56 SimCLR (ResNet-50) 87.8% – Paper Code 2020 79 of 137 ran · 58 unverified report
57 CPC 84.88% – Paper Code 2018 29 of 45 ran · 16 unverified report
58 S4L-Rotation (ResNet-50) 83.82% – Paper Code 2019 0 of 19 ran · 19 unverified report
59 Rotation (joint training) 83.82% – Paper – 2019 no code linked report
60 PIRL (ResNet-50) 83.8% – Paper Code 2019 3 of 4 ran · 1 unverified report
61 S4L-Exemplar (ResNet-50) 83.72% – Paper Code 2019 0 of 19 ran · 19 unverified report
62 Exemplar (joint training) 83.72% – Paper Code 2019 0 of 19 ran · 19 unverified report
63 VAT + Entropy Minimization (ResNet-50) 83.39% – Paper Code 2019 0 of 19 ran · 19 unverified report
64 VAT + Entropy Minimization 83.39% – Paper Code 2019 0 of 19 ran · 19 unverified report
65 VAT (ResNet-50) 82.78% – Paper Code 2019 0 of 19 ran · 19 unverified report
66 VAT 82.78% – Paper Code 2019 0 of 19 ran · 19 unverified report
67 Pseudolabeling (ResNet-50) 82.41% – Paper Code 2019 0 of 19 ran · 19 unverified report
68 Pseudolabeling 82.41% – Paper Code 2019 0 of 19 ran · 19 unverified report
69 Exemplar Fine-tuned (ResNet-50) 81.01% – Paper Code 2019 0 of 19 ran · 19 unverified report
70 Exemplar 81.01% – Paper Code 2019 0 of 19 ran · 19 unverified report
71 BigBiGAN (RevNet-50 ×4, BN+CReLU) 78.8% – Paper Code 2019 0 of 3 ran · 3 unverified report
72 Rotation Fine-tuned (ResNet-50) 78.53% – Paper Code 2019 0 of 19 ran · 19 unverified report
73 Rotation 78.53% – Paper Code 2019 0 of 19 ran · 19 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 of M ran · U unverified": of the M code samples Syntology harvested from repositories linked to that row's paper (joined by arXiv id), N executed on a synthesized input and the other U = M−N are unverified (harvested, no recorded 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; 23 rows (19 papers) have at least one sample that ran. Counting each paper once: Syntology ran 244 of 479 samples; 235 unverified. Separately, 149 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. Read from the graph 2026-09-24. Per-sample status is on the paper page.

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