Generalized zero-shot learning(GZSL) aims to classify samples from seen and unseen labels, assuming unseen labels are not accessible during training. Recent advancements in GZSL have been expedited by incorporating contrastive-learning-based (instance-based) embedding in generative networks and leveraging the semantic relationship between data points. However, existing embedding architectures suffer from two limitations: (1) limited discriminability of synthetic features' embedding without considering fine-grained cluster structures; (2) inflexible optimization due to restricted scaling mechanisms on existing contrastive embedding networks, leading to overlapped representations in the embedding space. To enhance the quality of representations in the embedding space, as mentioned in (1), we propose a margin-based prototypical contrastive learning embedding network that reaps the benefits of prototype-data (cluster quality enhancement) and implicit data-data (fine-grained representations) interaction while providing substantial cluster supervision to the embedding network and the generator. To tackle (2), we propose an instance adaptive contrastive loss that leads to generalized representations for unseen labels with increased inter-class margin. Through comprehensive experimental evaluation, we show that our method can outperform the current state-of-the-art on three benchmark datasets. Our approach also consistently achieves the best unseen performance in the GZSL setting.

翻译：广义零样本学习（GZSL）旨在对来自可见标签和不可见标签的样本进行分类，其假设在训练期间无法获取不可见标签。近年来，通过将基于对比学习（基于实例）的嵌入融入生成网络，并利用数据点之间的语义关系，GZSL 研究取得了显著进展。然而，现有的嵌入架构存在两个局限：（1）合成特征嵌入的区分能力有限，未能考虑细粒度的聚类结构；（2）由于现有对比嵌入网络中的缩放机制受限，导致优化不灵活，进而造成嵌入空间中表示的重叠。为解决（1）中所述提升嵌入空间表示质量的问题，我们提出了一种基于边界的原型对比学习嵌入网络，该网络既能利用原型-数据（聚类质量提升）和隐式数据-数据（细粒度表示）交互，又能为嵌入网络和生成器提供充分的聚类监督。针对（2），我们提出了一种实例自适应对比损失，通过增大类间边界，为不可见标签生成泛化的表示。通过全面的实验评估，我们证明该方法在三个基准数据集上均能超越当前的先进水平。同时，我们的方法在 GZSL 设置中持续实现了最优的不可见样本性能。