Codesota · Computer Vision · Image Classification · ImageNetTasks/Computer Vision/Image Classification
Image Classification · benchmark dataset · 2009 · N/A

ImageNet (ILSVRC).

ImageNet Large Scale Visual Recognition Challenge (ILSVRC): the standard 1,000-class image classification benchmark. Sparked the deep learning revolution from 2010 onward.

Paper ↗Download datasetSubmit a result ↵
§ 01 · Leaderboard

Best published scores.

15 results indexed across 2 metrics. Shaded row marks current SOTA; ties broken by submission date.

Primary
top-1-accuracy · higher is better
All metrics
top-1-accuracy, top-5-accuracy
top-1-accuracy· primary
10 rows
#ModelOrgSubmittedPaper / codetop-1-accuracy
01CoCa (ViT-G/14)OSSGoogleMay 2022CoCa: Contrastive Captioners are Image-Text Foundation M…91
02SoViT-400M/14OSSGoogleMay 2023codesota-editorial90.30
03EVA-02 (ViT-L/14+)OSSBAAIMar 2023EVA-02: A Visual Representation Powerhouse for Dense Rec…90
04ViT-22B/14OSSGoogleFeb 2023codesota-editorial89.51
05InternViT-6B (InternVL)OSSOpenGVLabJun 2024InternVL: Scaling up Vision Foundation Models88.20
06maxvit_base_tf_512.in1kOSSGoogleApr 2023codesota-editorial86.60
07coatnet_2_rw_224.sw_in12k_ft_in1kOSSGoogleSep 2022codesota-editorial86.58
08nextvit_large.bd_ssld_6m_in1k_384OSSByteDanceNov 2022codesota-editorial86.54
09swin_large.ms_in22k_ft_in1kOSSMicrosoftMar 2021Swin Transformer: Hierarchical Vision Transformer using …86.33
10convnext_base.fb_in22k_ft_in1kOSSMeta AIJan 2022codesota-editorial86.30
top-5-accuracy
5 rows
#ModelOrgSubmittedPaper / codetop-5-accuracy
01SENetOSSMomentaJan 2017codesota-editorial97.75
02ResNet-152OSSMicrosoftJan 2015codesota-editorial96.43
03GoogLeNetOSSGoogleJan 2014codesota-editorial93.30
04AlexNetOSSU. TorontoJan 2012codesota-editorial83.60
05NEC-UIUCOSSNEC / UIUCJan 2010codesota-editorial71.80
Fig 2 · Rows sorted by score within each metric. Shaded row marks SOTA. Dates reflect model or paper release where available, otherwise the date Codesota accessed the source.
§ 03 · Progress

2 steps
of state of the art.

Each row below marks a model that broke the previous record on top-1-accuracy. Intermediate submissions are kept in the leaderboard above; only SOTA-setting entries are re-listed here.

Higher scores win. Each subsequent entry improved upon the previous best.

SOTA line · top-1-accuracy
  1. Mar 1, 2021swin_large.ms_in22k_ft_in1kMicrosoft86.33
  2. May 1, 2022CoCa (ViT-G/14)Google91
Fig 3 · SOTA-setting models only. 2 entries span Mar 2021 → May 2022.
§ 04 · Literature

4 papers
tied to this benchmark.

Every paper below corresponds to at least one row in the leaderboard above. Click through for the arXiv preprint and, when available, the reference implementation.

§ 06 · Contribute

Have a score that beats
this table?

Submit a checkpoint and a reproduction script. We will run it, publish the score, and — if it takes the top — annotate the step on the progress chart with your name.

Submit a result ↵Read submission guide
What a submission needs
  • 01A public checkpoint or API endpoint
  • 02A reproduction script with frozen commit + seed
  • 03Declared evaluation environment (Python, deps)
  • 04One row per metric declared by this dataset
  • 05A contact so we can follow up on discrepancies
ImageNet — Image Classification benchmark · Codesota | CodeSOTA