Datasets › VizWiz-Classification
VizWiz-Classification
Our goal is to improve upon the status quo for designing image classification models trained in one domain that perform well on images from another domain. Complementing existing work in robustness testing, we introduce the first test dataset for this purpose which comes from an authentic use case where photographers wanted to learn about the content in their images. We built a new test set using 8,900 images taken by people who are blind for which we collected metadata to indicate the presence versus absence of 200 ImageNet object categories. We call this dataset VizWiz-Classification.
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.
| First row (archive order) | Paper | Code | ||||
|---|---|---|---|---|---|---|
| Domain Generalization | VizWiz-Classification | VOLO-D5 Accuracy - All Images 57.2 | VOLO: Vision Outlooker for Visual Recognition | rwightman/pytorch-image-models +6 | 90 | Compare |
| Image Classification | VizWiz-Classification | VOLO-D5 Accuracy 57.2 | VOLO: Vision Outlooker for Visual Recognition | rwightman/pytorch-image-models +6 | 1 | Compare |
| Multi-Label Image Classification | VizWiz-Classification | ResNet151 Accuracy 47.5 | Deep Residual Learning for Image Recognition | tensorflow/models +483 | 1 | Compare |
Papers archive 2025-07-28
19 shown of 19 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 22. 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 | |||
|---|---|---|---|---|
| A ConvNet for the 2020s | 54 | 1 | 10 Jan 2022 | ran 54 of 80 samples (26 unverified; 11 pointer-only for licence) |
| ResNet strikes back: An improved training procedure in timm | 14 | 1 | 1 Oct 2021 | ran 0 of 3 samples (3 unverified) |
| VOLO: Vision Outlooker for Visual Recognition | 7 | 2 | 24 Jun 2021 | ran 1 of 6 samples (5 unverified) |
| An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale | 158 | 2 | 22 Oct 2020 | ran 281 of 419 samples (138 unverified; 154 pointer-only for licence) |
| Measuring Robustness to Natural Distribution Shifts in Image Classification | 1 | 13 | 1 Jul 2020 | not harvested |
| The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization | 1 | 2 | 29 Jun 2020 | ran 13 of 14 samples (1 unverified) |
| AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty | 15 | 1 | 5 Dec 2019 | ran 43 of 51 samples (8 unverified; 25 pointer-only for licence) |
| Adversarial Examples Improve Image Recognition | 6 | 9 | 21 Nov 2019 | ran 2 of 2 samples (0 unverified) |
| RandAugment: Practical automated data augmentation with a reduced search space | 19 | 2 | 30 Sep 2019 | ran 58 of 65 samples (7 unverified; 17 pointer-only for licence) |
| AutoAugment: Learning Augmentation Strategies From Data | 3 | 4 | 1 Jun 2019 | not harvested |
| EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks | 144 | 6 | 28 May 2019 | ran 171 of 302 samples (131 unverified; 112 pointer-only for licence) |
| Adversarial Training for Free! | 6 | 1 | 29 Apr 2019 | ran 1 of 1 samples (0 unverified; 1 pointer-only for licence) |
| Making Convolutional Networks Shift-Invariant Again | 7 | 27 | 25 Apr 2019 | ran 2 of 4 samples (2 unverified; 3 pointer-only for licence) |
| Bag of Tricks for Image Classification with Convolutional Neural Networks | 28 | 1 | 4 Dec 2018 | ran 4 of 15 samples (11 unverified; 5 pointer-only for licence) |
| ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness | 7 | 3 | 29 Nov 2018 | ran 0 of 6 samples (6 unverified) |
| AutoAugment: Learning Augmentation Policies from Data | 33 | 4 | 24 May 2018 | ran 6 of 43 samples (37 unverified; 2 pointer-only for licence) |
| Aggregated Residual Transformations for Deep Neural Networks | 61 | 1 | 16 Nov 2016 | ran 34 of 80 samples (46 unverified; 13 pointer-only for licence) |
| Deep Residual Learning for Image Recognition | 484 | 4 | 10 Dec 2015 | ran 230 of 377 samples (147 unverified; 187 pointer-only for licence) |
| Very Deep Convolutional Networks for Large-Scale Image Recognition | 305 | 8 | 4 Sep 2014 | ran 12 of 122 samples (110 unverified; 4 pointer-only for licence) |
Dataset loaders archive 2025-07-28
1 loader as listed in the archive; links are outbound and not re-checked here.
Tasks archive 2025-07-28
License archive 2025-07-28
No licence recorded in the archive. Absence here is not a statement about the dataset's terms.
Modalities archive 2025-07-28
Languages archive 2025-07-28
No language tagged.
Variants archive 2025-07-28
- VizWiz-Classification
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