Datasets › shape bias

shape bias

Introduced by Robert Geirhos et al. in ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness29 Nov 2018 archive 2025-07-28

The 'shape bias' dataset was introduced in Geirhos et al. (ICLR 2019) and consists of 224x224 images with conflicting texture and shape information (e.g., cat shape with elephant texture). This is used to measure the shape vs. texture bias of image classifiers.

Benchmarks archive 2025-07-28

All 1 leaderboard 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.

First row (archive order)PaperCode
Object Recognition shape bias Imagen shape bias 98.7 Intriguing properties of generative classifiers SamsungSAILMontreal/ForestDiffusion 18 Compare

Papers archive 2025-07-28

papers with a benchmark row: 8 · with a code link: 7 · where Syntology ran a sample: 4 (4 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 (4 of 8 with a benchmark row: 4 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 8 of 8 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 120. 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
Intriguing properties of generative classifiers 1 3 28 Sep 2023 10 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; 3 where Syntology's instrument failed) · 2 unverified (12 pointer-only for licence)
Scaling Vision Transformers to 22 Billion Parameters 1 3 10 Feb 2023 not harvested
Learning Transferable Visual Models From Natural Language Supervision 82 1 26 Feb 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 (16 pointer-only for licence)
Do Adversarially Robust ImageNet Models Transfer Better? 2 1 16 Jul 2020 not harvested
A Simple Framework for Contrastive Learning of Visual Representations 96 3 13 Feb 2020 official (archive's flag): 2 ran · 115 ran (of which 33 constructed an object rather than computing a result; 89 with no instrument failure: 1 honoured, 1 violated, 87 with no contract checked; 26 where Syntology's instrument failed) · 22 unverified (52 pointer-only for licence)
The Origins and Prevalence of Texture Bias in Convolutional Neural Networks 0 1 20 Nov 2019 not harvested
Billion-scale semi-supervised learning for image classification 4 2 2 May 2019 not harvested
ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness 7 4 29 Nov 2018 community repositories only · 3 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; 0 where Syntology's instrument failed) · 3 unverified

Dataset loaders archive 2025-07-28

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

Tasks archive 2025-07-28

License archive 2025-07-28

CC-BY 4.0

Modalities archive 2025-07-28

Languages archive 2025-07-28

No language tagged.

Variants archive 2025-07-28

  • shape bias

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