Data-efficient image classification using deep neural networks in settings, where only small amounts of labeled data are available, has been an active research area in the recent past. However, an objective comparison between published methods is difficult, since existing works use different datasets for evaluation and often compare against untuned baselines with default hyper-parameters. We design a benchmark for data-efficient image classification consisting of six diverse datasets spanning various domains (e.g., natural images, medical imagery, satellite data) and data types (RGB, grayscale, multispectral). Using this benchmark, we re-evaluate the standard cross-entropy baseline and eight methods for data-efficient deep learning published between 2017 and 2021 at renowned venues. For a fair and realistic comparison, we carefully tune the hyper-parameters of all methods on each dataset. Surprisingly, we find that tuning learning rate, weight decay, and batch size on a separate validation split results in a highly competitive baseline, which outperforms all but one specialized method and performs competitively to the remaining one.
翻译:在只有少量标签数据的环境里,利用深神经网络进行数据高效图像分类是最近一个积极的研究领域,但是,对公布的方法进行客观比较是困难的,因为现有作品使用不同的数据集进行评价,而且常常与默认超参数的未调整基线进行比较。我们设计了一个数据高效图像分类基准,包括六个不同领域的不同数据集(例如自然图像、医疗图像、卫星数据)和数据类型(RGB、灰度、多光谱)。使用这一基准,我们重新评估2017年至2021年在著名地点公布的标准的跨渗透性基线和八种数据高效深层学习方法。为了进行公平和现实的比较,我们仔细调整每个数据集上所有方法的超参数。令人惊讶的是,我们发现在一个高度竞争性的基线中调整学习率、重量衰减和批量大小,在一个不同的验证分解结果上,该基准比所有方法都优于一种专门方法,并具有竞争力地与其余的基线相比。