Neuro-symbolic integration aims at harnessing the power of symbolic knowledge representation combined with the learning capabilities of deep neural networks. In particular, Logic Tensor Networks (LTNs) allow to incorporate background knowledge in the form of logical axioms by grounding a first order logic language as differentiable operations between real tensors. Yet, few studies have investigated the potential benefits of this approach to improve zero-shot learning (ZSL) classification. In this study, we present the Fuzzy Logic Visual Network (FLVN) that formulates the task of learning a visual-semantic embedding space within a neuro-symbolic LTN framework. FLVN incorporates prior knowledge in the form of class hierarchies (classes and macro-classes) along with robust high-level inductive biases. The latter allow, for instance, to handle exceptions in class-level attributes, and to enforce similarity between images of the same class, preventing premature overfitting to seen classes and improving overall performance. FLVN reaches state of the art performance on the Generalized ZSL (GZSL) benchmarks AWA2 and CUB, improving by 1.3% and 3%, respectively. Overall, it achieves competitive performance to recent ZSL methods with less computational overhead. FLVN is available at https://gitlab.com/grains2/flvn.

翻译：神经符号整合旨在利用符号知识表示的能力，并结合深度神经网络的学习能力。特别地，逻辑张量网络（Logic Tensor Networks, LTNs）通过将一阶逻辑语言作为实值张量之间的可微操作进行具体化，从而允许以逻辑公理的形式融入背景知识。然而，目前很少有研究探讨这种方法在提升零样本学习（Zero-Shot Learning, ZSL）分类中的潜在优势。在本研究中，我们提出了模糊逻辑视觉网络（Fuzzy Logic Visual Network, FLVN），它在神经符号LTN框架内将学习视觉-语义嵌入空间的任务形式化。FLVN 不仅融入了以类层次结构（类和宏类）形式存在的先验知识，还引入了稳健的高级归纳偏置。后者允许处理类级属性中的例外情况，并强制同类别图像之间的相似性，从而防止对已见类别过早过拟合，并提升整体性能。FLVN 在广义零样本学习（Generalized ZSL, GZSL）基准数据集 AWA2 和 CUB 上达到了最先进性能，分别提升了 1.3% 和 3%。总体而言，它在计算开销更少的情况下，与近期ZSL方法相比取得了具有竞争力的性能。FLVN 的代码可在 https://gitlab.com/grains2/flvn 获取。