Datasets › ImageNet-Sketch

ImageNet-Sketch

Introduced by Haohan Wang et al. in Learning Robust Global Representations by Penalizing Local Predictive Power29 May 2019 archive 2025-07-28

ImageNet-Sketch data set consists of 50,889 images, approximately 50 images for each of the 1000 ImageNet classes. The data set is constructed with Google Image queries "sketch of __", where __ is the standard class name. Only within the "black and white" color scheme is searched. 100 images are initially queried for every class, and the pulled images are cleaned by deleting the irrelevant images and images that are for similar but different classes. For some classes, there are less than 50 images after manually cleaning, and then the data set is augmented by flipping and rotating the images.

Source: ImageNet-Sketch Image Source: https://github.com/HaohanWang/ImageNet-Sketch

Benchmarks archive 2025-07-28

All 3 leaderboards whose dataset resolves to this page shown (sort by any header). "First row" is the archive's own first row at snapshot, in the archive's row order; nothing here re-ranks and metric direction is not asserted.

Syntology 2 newer papers were judged to report on this dataset's benchmarks so far (Claude Sonnet 4.5, reading their tables: a model's judgement, not a result; 0 placed): Image Classification · ImageNet-Sketch (2 judged, 0 placed). Drawn from 8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read).

First row (archive order)PaperCode
Domain Generalization ImageNet-Sketch Model soups (BASIC-L) Top-1 accuracy 77.18 Model soups: averaging weights of multiple fine-tuned... mlfoundations/model-soups +5 20 Compare
Zero-Shot Transfer Image Classification ImageNet-Sketch CoCa Accuracy (Private) 77.6 CoCa: Contrastive Captioners are Image-Text Foundation Models mlfoundations/open_clip +5 7 Compare
Image Classification ImageNet-Sketch µ2Net+ (ViT-L/16) Accuracy 88.6 A Continual Development Methodology for Large-scale... google-research/google-research 1 Compare

Papers archive 2025-07-28

papers with a benchmark row: 20 · with a code link: 18 · where Syntology ran a sample: 12 (12 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument) Syntology

Show: all papers with a benchmark rowonly where code ran (12 of 20 with a benchmark row: 12 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument)

Page 1 of 1: papers 1 to 20 of 20 with a leaderboard row on this dataset's benchmarks, newest first by the archive's date (ties by slug; undated papers last).

The archive's own "papers using this dataset" list was never published, so this is the benchmark-backed subset, not that list; the archive's count for this dataset is 268. The Syntology column is from Syntology's graph, stated per sample; it is not part of any archive number. A line 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” (C is a part of N, never taken away from it); the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. When the archive marks a repository official for the paper, the cell starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record.

PaperCodeResultsDateSamples run Syntology
EVA-CLIP-18B: Scaling CLIP to 18 Billion Parameters 2 1 6 Feb 2024 official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified (4 pointer-only for licence)
InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks 2 1 21 Dec 2023 community repositories only · 2 ran (of which 2 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) · 0 unverified; every one of the 2 samples that ran constructed an object rather than computing a result (2 pointer-only for licence)
Distilling Out-of-Distribution Robustness from Vision-Language Foundation Models 1 1 2 Nov 2023 official (archive's flag): 1 ran · 1 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; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result
EVA-CLIP: Improved Training Techniques for CLIP at Scale 4 1 27 Mar 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
A Whac-A-Mole Dilemma: Shortcuts Come in Multiples Where Mitigating One Amplifies Others 1 1 9 Dec 2022 not harvested
Context-Aware Robust Fine-Tuning 0 1 29 Nov 2022 not harvested
AltCLIP: Altering the Language Encoder in CLIP for Extended Language Capabilities 2 1 12 Nov 2022 official (archive's flag): 10 ran · 10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 1 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified (2 pointer-only for licence)
MetaFormer Baselines for Vision 8 6 24 Oct 2022 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
Generalized Parametric Contrastive Learning 4 1 26 Sep 2022 not harvested
Enhance the Visual Representation via Discrete Adversarial Training 1 1 16 Sep 2022 official (archive's flag): 9 ran · 10 ran (of which 5 constructed an object rather than computing a result; 7 with no instrument failure: 2 honoured, 0 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified (1 pointer-only for licence)
A Continual Development Methodology for Large-scale Multitask Dynamic ML Systems 1 1 15 Sep 2022 not harvested
CoCa: Contrastive Captioners are Image-Text Foundation Models 6 1 4 May 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 (2 pointer-only for licence)
Sequencer: Deep LSTM for Image Classification 5 1 4 May 2022 official (archive's flag): 4 ran · 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) · 5 unverified
Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time 6 2 10 Mar 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
Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervision 1 1 16 Feb 2022 not harvested
A ConvNet for the 2020s 54 1 10 Jan 2022 community repositories only · 57 ran (of which 39 constructed an object rather than computing a result; 49 with no instrument failure: 2 honoured, 0 violated, 47 with no contract checked; 8 where Syntology's instrument failed) · 23 unverified (12 pointer-only for licence)
Pyramid Adversarial Training Improves ViT Performance 1 2 30 Nov 2021 not harvested
Discrete Representations Strengthen Vision Transformer Robustness 1 1 20 Nov 2021 not harvested
Combined Scaling for Zero-shot Transfer Learning 0 1 19 Nov 2021 not harvested
Masked Autoencoders Are Scalable Vision Learners 58 1 11 Nov 2021 official: no sample here; runs from other or unrecorded repositories · 86 ran (of which 40 constructed an object rather than computing a result; 68 with no instrument failure: 8 honoured, 0 violated, 60 with no contract checked; 18 where Syntology's instrument failed) · 51 unverified (78 pointer-only for licence)

Dataset loaders archive 2025-07-28

4 loaders as listed in the archive; links are outbound and not re-checked here.

Tasks archive 2025-07-28

License archive 2025-07-28

Unknown

Modalities archive 2025-07-28

Languages archive 2025-07-28

No language tagged.

Variants archive 2025-07-28

  • ImageNet-Sketch

1 variant name, as the archive lists them.

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