DEIC Benchmark

Data-Efficient Image Classification Benchmark

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).

Images

벤치마크

Small Data Image Classification on DEIC Benchmark 결과 10개

Small Data Image Classification on ciFAIR-10 50 samples per class 결과 5개

Small Data Image Classification on CUB-200-2011, 30 samples per class 결과 4개

Small Data Image Classification on EuroSAT 50 samples per class 결과 3개

Small Data Image Classification on ImageNet 50 samples per class 결과 3개