Zero-shot classification is a generalization task where no instance from the
target classes is seen during training. To allow for test-time transfer, each
class is annotated with semantic information, commonly in the form of
attributes or text descriptions. While classical zero-shot learning does not
explicitly forbid using information from other datasets, the approaches that
achieve the best absolute performance on image benchmarks rely on features
extracted from encoders pretrained on Imagenet. This approach relies on
hyper-optimized Imagenet-relevant parameters from the supervised classification
setting, entangling important questions about the suitability of those
parameters and how they were learned with more fundamental questions about
representation learning and generalization. To remove these distractors, we
propose a more challenging setting: Zero-Shot Learning from scratch (ZFS),
which explicitly forbids the use of encoders fine-tuned on other datasets. Our
analysis on this setting highlights the importance of local information, and
compositional representations.

本文提出了一种更具挑战性的零样本学习方法，即从零开始的零样本学习（ZFS），该方法明确禁止使用在其他数据集上微调过的编码器，并强调了本地信息和组合表示的重要性。