Datasets › shape bias
shape bias
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) | Paper | Code | ||||
|---|---|---|---|---|---|---|
| Object Recognition | shape bias | Imagen shape bias 98.7 | Intriguing properties of generative classifiers | SamsungSAILMontreal/ForestDiffusion | 18 | Compare |
Papers archive 2025-07-28
8 shown of 8 papers with a leaderboard row on this dataset's benchmarks, newest first. The archive's own "papers using this dataset" list was never published, so this is the benchmark-backed subset; the archive's count for this dataset is 120. The Syntology column is from Syntology's graph (read 2026-09-24), stated per sample; it is not part of any archive number.
| Date | Samples run Syntology | |||
|---|---|---|---|---|
| Intriguing properties of generative classifiers | 1 | 3 | 28 Sep 2023 | ran 10 of 12 samples (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 | ran 16 of 20 samples (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 | ran 79 of 137 samples (58 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 | ran 0 of 6 samples (6 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
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