A Strong Baseline for the VIPriors Data-Efficient Image Classification Challenge

TL;DR

This paper introduces a robust baseline for data-efficient image classification on the VIPriors dataset, demonstrating that standard models and hyper-parameter tuning can achieve competitive accuracy without specialized methods.

Contribution

The authors establish a strong, simple baseline for the VIPriors challenge using standard techniques, highlighting the importance of hyper-parameter tuning over specialized methods.

Findings

Achieved 69.7% accuracy on VIPriors dataset.

Outperformed 50% of previous challenge submissions.

Showed standard models can be effective in data-efficient scenarios.

Abstract

Learning from limited amounts of data is the hallmark of intelligence, requiring strong generalization and abstraction skills. In a machine learning context, data-efficient methods are of high practical importance since data collection and annotation are prohibitively expensive in many domains. Thus, coordinated efforts to foster progress in this area emerged recently, e.g., in the form of dedicated workshops and competitions. Besides a common benchmark, measuring progress requires strong baselines. We present such a strong baseline for data-efficient image classification on the VIPriors challenge dataset, which is a sub-sampled version of ImageNet-1k with 100 images per class. We do not use any methods tailored to data-efficient classification but only standard models and techniques as well as common competition tricks and thorough hyper-parameter tuning. Our baseline achieves 69.7% accuracy on the VIPriors image classification dataset and outperforms 50% of submissions to the VIPriors 2021 challenge.