Datasets › DEIC Benchmark

DEIC Benchmark (Data-Efficient Image Classification Benchmark)

Introduced by Lorenzo Brigato et al. in Tune It or Don't Use It: Benchmarking Data-Efficient Image Classification30 Aug 2021 archive 2025-07-28

DEIC is a benchmark for measuring the data efficiency of models in the context of image classification. It is composed of 6 datasets that contain a small number of training samples per class (i.e., 30 < x < 80). It covers multiple image domains (i.e., natural images, fine-grained recognition, medical images, remote sensing, handwriting recognition) and data types (i.e., RGB, grayscale, multi-spectral).

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)PaperCode
Small Data Image Classification DEIC Benchmark Harmonic Networks Average Balanced Accuracy (across datasets) 68.70 Tune It or Don't Use It: Benchmarking Data-Efficient... cvjena/deic 10 Compare
Small Data Image Classification ciFAIR-10 50 samples per class ChimeraMix+AutoAugment Accuracy 70.09 ChimeraMix: Image Classification on Small Datasets via... creinders/chimeramix 5 Compare
Small Data Image Classification EuroSAT 50 samples per class Harmonic Networks Accuracy 92.09 Tune It or Don't Use It: Benchmarking Data-Efficient... cvjena/deic 3 Compare

Papers archive 2025-07-28

2 shown of 2 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 3. The Syntology column is from Syntology's graph (read 2026-09-24), stated per sample; it is not part of any archive number.

DateSamples run Syntology
ChimeraMix: Image Classification on Small Datasets via Masked Feature Mixing 1 2 23 Feb 2022 ran 5 of 5 samples (0 unverified)
Tune It or Don't Use It: Benchmarking Data-Efficient Image Classification 1 16 30 Aug 2021 not harvested

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

Custom

Modalities archive 2025-07-28

Languages archive 2025-07-28

No language tagged.

Variants archive 2025-07-28

  • CUB-200-2011, 30 samples per class
  • ImageNet 50 samples per class
  • ciFAIR-10
  • EuroSAT 50 samples per class
  • Data-Efficient Image Classification (DEIC) Benchmark
  • DEIC Benchmark
  • ciFAIR-10 50 samples per class

7 variant names, 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