</> Code with Papers by Syntology

Browse › Computer Vision › Domain Generalization › ImageNet-R

Domain Generalization archive 2025-07-28

ImageNet-R Benchmark (Domain Generalization)

39 rows 38 with code listed 1 metric Dataset page

The idea of Domain Generalization is to learn from one or multiple training domains, to extract a domain-agnostic model which can be applied to an unseen domain

Source: Diagram Image Retrieval using Sketch-Based Deep Learning and Transfer Learning

The archive carries no text for this table; the description above is the archive's text for the task Domain Generalization. archive 2025-07-28

Over time archive 2025-07-28

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

Not inferred: Top-1 Error Rate. Points are placed at the row's paper date; 39 of 39 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 Model soups (BASIC-L) 3.90 ✓ Paper Code 2022 5 of 17 ran · 12 unverified report
2 Model soups (ViT-G/14) 4.54 ✓ Paper Code 2022 5 of 17 ran · 12 unverified report
3 CAR-FT (CLIP, ViT-L/14@336px) 10.3 ✓ Paper – 2022 no code linked report
4 FAN-Hybrid-L(IN-21K, 384)) 28.9 ✓ Paper Code 2022 linked, not harvested report
5 CAFormer-B36 (IN21K, 384) 29.6 ✓ Paper Code 2022 0 of 4 ran · 4 unverified report
6 LLE (ViT-B/16, SWAG, Edge Aug) 31.3 ✓ Paper Code 2022 linked, not harvested report
7 CAFormer-B36 (IN21K) 31.7 ✓ Paper Code 2022 0 of 4 ran · 4 unverified report
8 ConvNeXt-XL (Im21k, 384) 31.8 ✓ Paper Code 2022 54 of 80 ran · 26 unverified report
9 LLE (ViT-H/14, MAE, Edge Aug) 33.1 – Paper Code 2022 linked, not harvested report
10 MAE (ViT-H, 448) 33.5 – Paper Code 2021 71 of 137 ran · 66 unverified report
11 ConvFormer-B36 (IN21K, 384) 33.5 ✓ Paper Code 2022 0 of 4 ran · 4 unverified report
12 MAE+DAT (ViT-H) 34.39 – Paper Code 2022 10 of 11 ran · 1 unverified report
13 ConvFormer-B36 (IN21K) 34.7 ✓ Paper Code 2022 0 of 4 ran · 4 unverified report
14 Discrete Adversarial Distillation (ViT-B,224) 34.9 – Paper Code 2023 1 of 1 ran · 0 unverified report
15 GPaCo (ViT-L) 39.7 – Paper Code 2022 linked, not harvested report
16 VOLO-D5+HAT 40.3 – Paper Code 2022 10 of 14 ran · 4 unverified report
17 Pyramid Adversarial Training Improves ViT (Im21k) 42.16 ✓ Paper Code 2021 linked, not harvested report
18 FAN-L-Hybrid+STL 43.4 – Paper Code 2024 linked, not harvested report
19 SEER (RegNet10B) 43.9 ✓ Paper Code 2022 linked, not harvested report
20 DiscreteViT 44.74 – Paper Code 2021 linked, not harvested report
21 CAFormer-B36 (384) 45 – Paper Code 2022 0 of 4 ran · 4 unverified report
22 Pyramid Adversarial Training Improves ViT 46.08 – Paper Code 2021 linked, not harvested report
23 CAFormer-B36 46.1 – Paper Code 2022 0 of 4 ran · 4 unverified report
24 ConvFormer-B36 (384) 47.8 – Paper Code 2022 0 of 4 ran · 4 unverified report
25 ConvFormer-B36 48.9 – Paper Code 2022 0 of 4 ran · 4 unverified report
26 RVT-B* 51.3 – Paper Code 2021 linked, not harvested report
27 Sequencer2D-L 51.9 – Paper Code 2022 4 of 9 ran · 5 unverified report
28 RVT-S* 52.3 – Paper Code 2021 linked, not harvested report
29 DeepAugment+AugMix (ResNet-50) 53.2 – Paper Code 2020 13 of 14 ran · 1 unverified report
30 PRIME with JSD (ResNet-50) 53.7 – Paper Code 2021 5 of 8 ran · 3 unverified report
31 RVT-Ti* 56.1 – Paper Code 2021 linked, not harvested report
32 PRIME (ResNet-50) 57.1 – Paper Code 2021 5 of 8 ran · 3 unverified report
33 DeepAugment (ResNet-50) 57.8 – Paper Code 2020 13 of 14 ran · 1 unverified report
34 Stylized ImageNet (ResNet-50) 58.5 ✓ Paper Code 2018 0 of 6 ran · 6 unverified report
35 AugMix (ResNet-50) 58.9 – Paper Code 2019 43 of 51 ran · 8 unverified report
36 ResNet-50 63.9 – Paper Code 2015 230 of 377 ran · 147 unverified report
37 ResNet-152x2-SAM 71.9 – Paper Code 2021 linked, not harvested report
38 ViT-B/16-SAM 73.6 – Paper Code 2021 linked, not harvested report
39 Mixer-B/8-SAM 76.5 – Paper Code 2021 linked, not harvested report

All 39 rows shown. 39 link to a paper page on this site; 13 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). 23 rows have a graph line, from 13 distinct papers; 14 rows (11 papers) have at least one sample that ran. Counting each paper once: Syntology ran 446 of 729 samples; 283 unverified. Separately, 297 of those 729 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