Modern deep learning requires large-scale extensively labelled datasets for training. Few-shot learning aims to alleviate this issue by learning effectively from few labelled examples. In previously proposed few-shot visual classifiers, it is assumed that the feature manifold, where classifier decisions are made, has uncorrelated feature dimensions and uniform feature variance. In this work, we focus on addressing the limitations arising from this assumption by proposing a variance-sensitive class of models that operates in a low-label regime. The first method, Simple CNAPS, employs a hierarchically regularized Mahalanobis-distance based classifier combined with a state of the art neural adaptive feature extractor to achieve strong performance on Meta-Dataset, mini-ImageNet and tiered-ImageNet benchmarks. We further extend this approach to a transductive learning setting, proposing Transductive CNAPS. This transductive method combines a soft k-means parameter refinement procedure with a two-step task encoder to achieve improved test-time classification accuracy using unlabelled data. Transductive CNAPS achieves state of the art performance on Meta-Dataset. Finally, we explore the use of our methods (Simple and Transductive) for "out of the box" continual and active learning. Extensive experiments on large scale benchmarks illustrate robustness and versatility of this, relatively speaking, simple class of models. All trained model checkpoints and corresponding source codes have been made publicly available.
翻译:现代深层学习需要大规模广泛贴标签的培训数据集。少见的学习旨在通过从少数贴标签的例子中有效地学习,减轻这一问题。在以前提议的少见的视觉分类中,假定作出分类决定的特征多重具有不相干的特点层面和统一的特征差异。在这项工作中,我们侧重于解决这一假设所产生的局限性,方法是提出在低标签制度下运行的对差异敏感的模型类别。第一种方法是简单 CNAPS,采用等级化固定的马哈拉诺比-距离分类器,加上一种艺术神经适应性特征提取器,以在Meta-Dataset、微型IMageNet和分层-IMageNet基准上取得强劲的性能。我们进一步将这一方法扩大到转换式学习环境,提出透明的 CNAPS。这种转基因方法将软K手段参数改进程序与两步制任务编码结合在一起,利用未贴标签的源数据改进测试-时间分类精度。转换的CPPS在M-DS、小型智能矩阵中,我们正在探索的常规和不断演练的常规,在Metal-Dal-Dravely road Stal rodeal pral bal rodustration rodustration rodustrislation rodustryal stal stal stal rodustration rodustrislation sal strislation sal stal strism sal sal stration sal stration sal sal stration sal strismal sal sal strismal lading astrational rodustration sal lading aglegleglegleglemental lades roglement sal lad.