Datasets › ReINs and RePLs: Challenging, small datasets for quick validations of designing deep neural networks for image classification

ReINs and RePLs: Challenging, small datasets for quick validations of designing deep neural networks for image classification

Efficiently rescaling a large dataset by adapting statistical computation to validation results of a pre-trained network.
A unified collection of the sensitive images and those in their confused classes would form a challenging tiny set.
An application for rescaling two large datasets: ImageNet and Places365 to obtain their rescaled subsets.
Experimental results for image classification have validated the raised challenge of the rescaled subsets. Verifying models on these helps researchers save the computational cost and the necessary time for the early network drafts.
It can be conducted that a network draft will obtain a good rate on large datasets if it is good on the rescaled subsets, correspondingly.

Benchmarks archive 2025-07-28

No leaderboard in the archive resolves to this dataset.

No paper in the archive has a leaderboard row on this dataset; the archive counts 1 paper for it but never published that list.

No loader listed in the archive.

No task tagged in the archive.

According to ImageNet's and Places365's

No modality tagged.

No language tagged.

ReINs and RePLs: Challenging, small datasets for quick validations of designing deep neural networks for image 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