One of the key limitations of modern deep learning approaches lies in the
amount of data required to train them. Humans, by contrast, can learn to
recognize novel categories from just a few examples. Instrumental
基于人类认知启发的 Recognition as Part Composition 图像编码方法,在零样本学习、少样本学习和无监督领域自适应等低样本泛化任务中,可以克服深度卷积神经网络面临的难题,并且在对抗攻击下比深度神经网络更具鲁棒性。此外,采用 RPC 图像编码器的分类器对人而言是可解释的。基于此,我们提出了一种应用解释性编码的方法,生成用于评估新数据集零样本学习方法的合成属性注释。