Dataset Open Access
SlimageNet64
Anonymous
Citation Style Language JSON Export
{
"publisher": "Zenodo",
"DOI": "10.5281/zenodo.3672132",
"author": [
{
"family": "Anonymous"
}
],
"issued": {
"date-parts": [
[
2020,
2,
7
]
]
},
"abstract": "<p>SlimageNet64 is new variant of ImageNet64×64 (Chrabaszcz et al., 2017), derived<br>\nfrom Slim and ImageNet. SlimageNet64 is ideal for few-shot learning, continual learning and meta-learning research. It consists of 200 instances from each of the 1000 object categories of the ILSVRC-2012 dataset (Krizhevsky et al., 2012; Russakovsky et al., 2015), for a total of 200K RGB images with a resolution of 64 × 64 × 3 pixels. We created this dataset from the downscaled version of ILSVRC-2012, ImageNet64x64, as reported in (Chrabaszcz et al., 2017), using the box downsampling Pillow library.</p>",
"title": "SlimageNet64",
"type": "dataset",
"id": "3672132"
}
698
582
views
downloads
| All versions | This version | |
|---|---|---|
| Views | 698 | 697 |
| Downloads | 582 | 582 |
| Data volume | 916.6 GB | 916.6 GB |
| Unique views | 634 | 633 |
| Unique downloads | 178 | 178 |
Indexed in
- Publication date:
- February 7, 2020
- DOI:
-
- Keyword(s):
- Few-Shot Learning, Continual Few-Shot Learning, Meta-Learning, Benchmark, Benchmarks, Dataset, Datasets
- License (for files):
- Other (Non-Commercial)