Browse › Computer Vision › Image Classification › ObjectNet

Image Classification archive 2025-07-28

ObjectNet Benchmark (Image Classification)

106 rows 83 with code listed 2 metrics Dataset page

Syntology Since the archive (Syntology): none placed; 2 newer papers judged to report on this board so far.

Image Classification is a fundamental task in vision recognition that aims to understand and categorize an image as a whole under a specific label. Unlike object detection, which involves classification and location of multiple objects within an image, image classification typically pertains to single-object images. When the classification becomes highly detailed or reaches instance-level, it is often referred to as image retrieval, which also involves finding similar images in a large database.

Source: Metamorphic Testing for Object Detection Systems

The archive carries no text for this table; the description above is the archive's text for the task 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). Points are placed at the row's paper date, not an evaluation date; 106 of 106 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 CoCa 82.7 ✓ Paper Code 2022 10 ran (of which 5 constructed an object rather than computing a result; 9 with no instrument failure: 2 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 7 unverified report
2 LiT 82.5 ✓ Paper Code 2021 linked, not harvested report
3 BASIC 82.3 ✓ Paper – 2021 no code linked report
4 EVA-02-CLIP-E/14+ 79.6 ✓ Paper Code 2023 community repositories only · 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) · 3 unverified report
5 Baseline (ViT-G/14) 79.03 ✓ Paper Code 2022 community repositories only · 10 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 5 where Syntology's instrument failed) · 7 unverified report
6 Model soups (ViT-G/14) 78.52 ✓ Paper Code 2022 community repositories only · 10 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 5 where Syntology's instrument failed) · 7 unverified report
7 MAWS (ViT-6.5B) 77.9 ✓ Paper Code 2023 linked, not harvested report
8 MAWS (ViT-2B) 75.8 ✓ Paper Code 2023 linked, not harvested report
9 MAWS (ViT-H) 72.6 ✓ Paper Code 2023 linked, not harvested report
10 CLIP 72.3 ✓ Paper Code 2021 official: no sample here; runs from other or unrecorded repositories · 16 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 14 where Syntology's instrument failed) · 4 unverified report
11 ALIGN 72.2 ✓ Paper – 2021 no code linked report
12 WiSE-FT 72.1 ✓ Paper Code 2021 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) · 2 unverified report
13 ViT-e 72.0 – Paper Code 2022 official (archive's flag): 2 ran · 2 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified report
14 ViT-G/14 70.53 ✓ Paper Code 2021 linked, not harvested report
15 SWAG (ViT H/14) 69.5 ✓ Paper Code 2022 linked, not harvested report
16 NS (Eff.-L2) 68.5 ✓ Paper Code 2021 linked, not harvested report
17 RegNetY 128GF (Platt) 64.3 ✓ Paper Code 2022 linked, not harvested report
18 LLE (ViT-H/14, MAE, Edge Aug) 60.78 – Paper Code 2022 linked, not harvested report
19 SEER (RegNet10B) 60.2 ✓ Paper Code 2022 linked, not harvested report
20 ViT H/14 (Platt) 60 ✓ Paper Code 2022 linked, not harvested report
21 BiT-L (ResNet-152x4) 58.780 ✓ Paper Code 2019 community repositories only · 9 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 1 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified report
22 ViT L/16 (Platt) 57.3 ✓ Paper Code 2022 linked, not harvested report
23 Vit B/16 (Bamboo) 53.9 ✓ Paper Code 2022 official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 2 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified report
24 AR-L (Opt Relevance) 52.073.5 ✓ Paper Code 2022 linked, not harvested report
25 ALIGN-MRL 51.6 ✓ Paper Code 2022 official: harvested, nothing 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
26 ViT-B/16 (ANN-1.3B) 50.7 ✓ Paper – 2021 no code linked report
27 ViT-B/16 (512x512) + Pyramid 49.39 ✓ Paper Code 2021 linked, not harvested report
28 ResNet-101 (JFT-300M) 49.1 ✓ Paper – 2021 no code linked report
29 ViT B/16 48.9 ✓ Paper Code 2022 linked, not harvested report
30 ViT-B/32 48.4 ✓ Paper – 2021 no code linked report
31 ViT-B/16 (512x512) + Pixel 47.53 ✓ Paper Code 2021 linked, not harvested report
32 AR-B (Opt Relevance) 47.170 ✓ Paper Code 2022 linked, not harvested report
33 BiT-M (ResNet-152x4) 47.069 ✓ Paper Code 2019 community repositories only · 9 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 1 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified report
34 ViT-B/16 (512x512) 46.68 ✓ Paper Code 2021 linked, not harvested report
35 ViT-B (Discrete 512x512) 46.62 ✓ Paper Code 2021 linked, not harvested report
36 AR-L 46.568.3 ✓ Paper Code 2022 linked, not harvested report
37 ViT-L (Opt Relevance) 43.265.8 ✓ Paper Code 2022 linked, not harvested report
38 CLIP L 42.80 ✓ Paper Code 2021 official (archive's flag): 4 ran · 4 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; 1 where Syntology's instrument failed) · 2 unverified report
39 ResNet-50 (JFT-300M) 42.5 ✓ Paper – 2021 no code linked report
40 ViT-B (Opt Relevance) 42.265.1 ✓ Paper Code 2022 linked, not harvested report
41 CLIP L (LAION) 42.10 ✓ Paper Code 2021 official (archive's flag): 4 ran · 4 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; 1 where Syntology's instrument failed) · 2 unverified report
42 AR-B 41.463.7 ✓ Paper Code 2022 linked, not harvested report
43 RegViT on 384x384 + Adv Pyramid 39.79 ✓ Paper Code 2021 linked, not harvested report
44 ResNet-152 + GenInt with Transfer 39.3861.43 ✓ Paper Code 2020 linked, not harvested report
45 AR-S (Opt Relevance) 39.361.7 ✓ Paper Code 2022 linked, not harvested report
46 ResNet-50 (Bamboo) 38.8 ✓ Paper Code 2022 official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 2 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified report
47 RegViT on 384x384 + Adv Pixel 37.41 ✓ Paper Code 2021 linked, not harvested report
48 ViT-L 37.459.5 ✓ Paper Code 2022 linked, not harvested report
49 DeiT-L (Opt Relevance) 36.356.6 ✓ Paper Code 2022 linked, not harvested report
50 BiT-S (ResNet-152x4) 36.057 ✓ Paper Code 2019 community repositories only · 9 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 1 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified report
51 NASNet-A 35.7756.05 ✓ Paper – 2019 no code linked report
52 PNASNet-5L 35.6354.95 ✓ Paper – 2019 no code linked report
53 RegViT on 384x384 35.59 ✓ Paper Code 2021 linked, not harvested report
54 ViT-B 35.156.4 ✓ Paper Code 2022 linked, not harvested report
55 RegViT on 384x384 + Random Pyramid 34.83 ✓ Paper Code 2021 linked, not harvested report
56 AR-S 34.355.8 ✓ Paper Code 2022 linked, not harvested report
57 RegViT on 384x384 + Random Pixel 34.12 ✓ Paper Code 2021 linked, not harvested report
58 RegViT (RandAug) + Adv Pyramid 32.92 ✓ Paper Code 2021 linked, not harvested report
59 Inception-v4 32.2451.98 ✓ Paper – 2019 no code linked report
60 DeiT-S (Opt Relevance) 31.653 ✓ Paper Code 2022 linked, not harvested report
61 ResNet-50 + CGC 31.5350.16 ✓ Paper Code 2019 linked, not harvested report
62 DeiT-L 31.448.5 ✓ Paper Code 2022 linked, not harvested report
63 Discrete ViT + Pixel 30.98 ✓ Paper Code 2021 linked, not harvested report
64 Discrete ViT + Pyramid 30.28 ✓ Paper Code 2021 linked, not harvested report
65 RegViT (RandAug) + Adv Pixel 30.11 ✓ Paper Code 2021 linked, not harvested report
66 Discrete ViT 29.95 ✓ Paper Code 2021 linked, not harvested report
67 ResNet-152 29.5949.4 ✓ Paper – 2019 no code linked report
68 RegViT (RandAug) + Random Pyramid 29.41 ✓ Paper Code 2021 linked, not harvested report
69 RegViT (RandAug) 29.3 ✓ Paper Code 2021 linked, not harvested report
70 ResNet-50 + GroupNorm 29.250.2 ✓ 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
71 ResNet-50 + RoHL 29.2 ✓ 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
72 RegViT (RandAug) + Random Pixel 28.72 ✓ Paper Code 2021 linked, not harvested report
73 MLP-Mixer + Pyramid 28.6 ✓ Paper Code 2021 linked, not harvested report
74 ResNet-50 + FixUp 28.548.6 ✓ 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
75 ResNet-50 + MixUp (rescaled) 28.37 ✓ Paper Code 2020 linked, not harvested report
76 DeiT-S 28.347.3 ✓ Paper Code 2022 linked, not harvested report
77 ResNet-18 + GenInt with Transfer 27.0348.02 ✓ Paper Code 2020 linked, not harvested report
78 MLP-Mixer 25.9 ✓ Paper Code 2021 linked, not harvested report
79 RELICv2 25.9 ✓ 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
80 ViT + MixUp 25.65 ✓ Paper Code 2021 linked, not harvested report
81 C-BYOL 25.5 ✓ Paper Code 2021 official (archive's flag): 7 ran · 7 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; 0 where Syntology's instrument failed) · 5 unverified report
82 MLP-Mixer + Pixel 24.75 ✓ Paper Code 2021 linked, not harvested report
83 BYOL (BG_RM) 23.9 ✓ Paper – 2021 no code linked report
84 RELIC 23.8 ✓ 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
85 BYOL 23 ✓ 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
86 SwAV (BG_RM) 21.9 ✓ Paper – 2021 no code linked report
87 ViT + CutMix 21.61 ✓ Paper Code 2021 linked, not harvested report
88 MoCo-v2 (BG_Swaps) 20.8 ✓ Paper – 2021 no code linked report
89 C-SimCLR 20.8 ✓ Paper Code 2021 official (archive's flag): 7 ran · 7 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; 0 where Syntology's instrument failed) · 5 unverified report
90 SeLa(v2) (reverse linear probing) 20.6148.83 ✓ Paper – 2021 no code linked report
91 DILEMMA 20.51 ✓ Paper Code 2022 linked, not harvested report
92 DeepCluster(v2) (reverse linear probing) 19.7346.81 ✓ Paper – 2021 no code linked report
93 VGG-14 19.1337.15 ✓ Paper – 2019 no code linked report
94 ResNet-50 (ImageNet-Captions) 18.70 ✓ Paper Code 2022 linked, not harvested report
95 SwAV (reverse linear probing) 17.7143.64 ✓ Paper – 2021 no code linked report
96 ViT 17.36 ✓ Paper Code 2021 linked, not harvested report
97 ResNet34-RPG 16.5 ✓ Paper Code 2021 official (archive's flag): 3 ran · 3 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; 2 where Syntology's instrument failed) · 0 unverified report
98 CLIP (CC12M pretrain) 15.24 ✓ Paper – 2022 no code linked report
99 SimCLR 14.6 ✓ 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
100 ResNet-152 (FRCNN-ag-ad, VOC) 13.229.7 ✓ Paper – 2020 no code linked report
101 MoCo(v2) (reverse linear probing) 12.6731.45 ✓ Paper – 2021 no code linked report
102 MoCHi (reverse linear probing) 12.6431.71 ✓ Paper – 2021 no code linked report
103 OBoW (reverse linear probing) 12.2331.72 ✓ Paper – 2021 no code linked report
104 AlexNet 6.7817.6 ✓ Paper – 2019 no code linked report
105 BigBiGAN (RevNet-50 4×) 4.92 ✓ Paper Code 2020 official (archive's flag): 8 ran · 8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified report
106 ViT-H/14 82.1 ✓ Paper Code 2020 official: harvested, nothing ran · 307 ran (of which 165 constructed an object rather than computing a result; 286 with no instrument failure: 8 honoured, 2 violated, 276 with no contract checked; 21 where Syntology's instrument failed) · 112 unverified report

All 106 rows shown. 106 link to a paper page on this site; 104 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). 27 rows have a graph line, from 16 distinct papers. Rows whose paper has a sample that ran: 27 (22 with a run with no instrument failure, 5 where every run was a failure of Syntology's instrument). Papers: 16 with a sample that ran: 13 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 27 rows with a graph line, 26 have an archive-official repository: on 17 a sample from it ran (13 with a run with no instrument failure), on 6 the samples that ran came from community repositories only, and on 1 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 549 samples: 399 ran (of which 174 constructed an object rather than computing a result; 345 with no instrument failure: 12 honoured, 7 violated, 326 with no contract checked; 54 where Syntology's instrument failed) · 150 unverified. Separately, 177 of those 549 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), 2 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 1,595 of the 8,888 were already full without this board, so if it was crowded out of them it is not counted), and 2 proposed a result; of those 2, 2 gave no cell that passed the extractor's own checks, 0 were rejected by the independent check, 0 await a verdict and 0 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.

Newer papers whose tables Claude Sonnet 4.5 judged to report on this benchmark (a model's judgement, not a result; newest first by arXiv id)

Paper arXiv date Ran Syntology Outcome
TRACER: Persistent Regularization for Robust Multimodal Finetuning arXiv:2605.29380 28 May 2026 9 harvested: 5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified refused by a rule: the table's column header does not name the leaderboard's metric
Concept-Guided Fine-Tuning: Steering ViTs away from Spurious Correlations to Improve Robustness arXiv:2603.08309 9 Mar 2026 3 harvested: 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 refused by rules: the table's column header does not name the leaderboard's metric; one configuration gave two values for one column

Syntology 2 newer papers judged to report on this board: the papers counted above as having proposed a result (0 placed); every one is listed here and in the JSON twin. The order is the arXiv identifier's, newest first, not a rank. The judgement is the model's, read from the paper's own tables; the outcome is what Syntology's checks did with it, and no value from a paper that was not placed is printed. “refused by a rule” names the extractor's rule; “no cell passed the extractor's checks” means the extractor's record holds no cell for this board, passed or refused. The 2 counted above as giving no cell that passed the extractor's own checks are the 2 marked “refused by a rule”. Drawn from 8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read).

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