Classification based on Zero-shot Learning (ZSL) is the ability of a model to classify inputs into novel classes on which the model has not previously seen any training examples. Providing an auxiliary descriptor in the form of a set of attributes describing the new classes involved in the ZSL-based classification is one of the favored approaches to solving this challenging task. In this work, inspired by Hyperdimensional Computing (HDC), we propose the use of stationary binary codebooks of symbol-like distributed representations inside an attribute encoder to compactly represent a computationally simple end-to-end trainable model, which we name Hyperdimensional Computing Zero-shot Classifier~(HDC-ZSC). It consists of a trainable image encoder, an attribute encoder based on HDC, and a similarity kernel. We show that HDC-ZSC can be used to first perform zero-shot attribute extraction tasks and, can later be repurposed for Zero-shot Classification tasks with minimal architectural changes and minimal model retraining. HDC-ZSC achieves Pareto optimal results with a 63.8% top-1 classification accuracy on the CUB-200 dataset by having only 26.6 million trainable parameters. Compared to two other state-of-the-art non-generative approaches, HDC-ZSC achieves 4.3% and 9.9% better accuracy, while they require more than 1.85x and 1.72x parameters compared to HDC-ZSC, respectively.

翻译：基于零样本学习（ZSL）的分类能力，是指模型能够对未曾在训练样本中出现过的新类别输入进行分类。在解决这一挑战性任务时，一种常用方法是以属性集的形式提供辅助描述符，描述ZSL分类中所涉及的新类别。受超维计算（HDC）启发，本文提出在属性编码器中使用静态二进制码本，以符号式分布式表示紧凑地构建计算简单的端到端可训练模型，命名为超维计算零样本分类器（HDC-ZSC）。该模型由可训练图像编码器、基于HDC的属性编码器和相似性核组成。研究表明，HDC-ZSC可先用于执行零样本属性提取任务，随后以最小的架构改动和极少的模型重训练，即可重新用于零样本分类任务。HDC-ZSC在CUB-200数据集上仅需2660万个可训练参数，即可达到63.8%的top-1分类准确率，实现帕累托最优结果。与另外两种最先进的非生成式方法相比，HDC-ZSC的准确率分别提升4.3%和9.9%，而这两种方法的参数数量分别是HDC-ZSC的1.85倍和1.72倍。