Generalized Zero-Shot Learning (GZSL) and Open-Set Recognition (OSR) are two mainstream settings that greatly extend conventional visual object recognition. However, the limitations of their problem settings are not negligible. The novel categories in GZSL require pre-defined semantic labels, making the problem setting less realistic; the oversimplified unknown class in OSR fails to explore the innate fine-grained and mixed structures of novel categories. In light of this, we are motivated to consider a new problem setting named Zero-Knowledge Zero-Shot Learning (ZK-ZSL) that assumes no prior knowledge of novel classes and aims to classify seen and unseen samples and recover semantic attributes of the fine-grained novel categories for further interpretation. To achieve this, we propose a novel framework that recovers the clustering structures of both seen and unseen categories where the seen class structures are guided by source labels. In addition, a structural alignment loss is designed to aid the semantic learning of unseen categories with their recovered structures. Experimental results demonstrate our method's superior performance in classification and semantic recovery on four benchmark datasets.
翻译:普通零热学习(GZSL) 和开放点识别(OSR) 是两大主流设置, 大大扩展了常规视觉对象的识别。 但是, 问题设置的局限性不容忽略。 GZSL 中的小类需要预先定义的语义标签, 使得问题设置不那么现实; OSR 中过于简单化的未知类别未能探索新类的精细和混合结构。 有鉴于此, 我们有志于考虑一个新的问题设置, 名为 Zero- knewledge Zero- Shot 学习( ZK- ZSL ), 假设它们没有新类知识, 目的是要对精细细细细细小类的样本进行分类和不可见的样本进行分类, 并恢复其语义属性, 以便进一步解释。 为了实现这一点, 我们提出了一个新框架, 在所见类结构以源标签为指导的地方, 恢复了所见和不可见类的组群落的群落结构。 此外, 结构性校准损失旨在帮助未知类的语义学习其回收结构。 实验结果显示我们的方法在分类和磁性四数据恢复的高级基准的高级业绩。