A Strong Baseline for the VIPriors Data-Efficient Image Classification Challenge
This work provides a benchmark for data-efficient learning in image classification, which is incremental as it uses standard techniques rather than novel approaches.
The paper tackles the problem of data-efficient image classification by establishing a strong baseline on the VIPriors challenge dataset, achieving 69.7% accuracy and outperforming 50% of submissions without using specialized methods.
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.