论文标题
带有知识增强视觉语义嵌入的零拍学习
Zero-Shot Learning with Knowledge Enhanced Visual Semantic Embeddings
论文作者
论文摘要
我们通过将常识性知识纳入DNN来改善零射击学习（ZSL）。我们提出了基于常识性的神经符号损失（CSNL），该神经符号损失（CSNL）作为新的神经符号损失函数提出了先验知识，可以使视觉声音嵌入正常。 CSNL强迫VSE中的视觉特征遵守与高鼻和属性有关的常识规则。我们介绍了改进学习的两个关键新颖性：（1）对小组的规则执行，而不是单个概念来考虑班级的关系，以及（2）逻辑运营商内部的信心余量，以启用隐式课程学习并防止过度过度拟合。我们评估合并每个知识源的优势，并在常规ZSL和广义ZSL中显示出对先前最新方法的一致收益。 AWA2，CUB和动力学的提高了11.5％，5.5％和11.6％。
We improve zero-shot learning (ZSL) by incorporating common-sense knowledge in DNNs. We propose Common-Sense based Neuro-Symbolic Loss (CSNL) that formulates prior knowledge as novel neuro-symbolic loss functions that regularize visual-semantic embedding. CSNL forces visual features in the VSE to obey common-sense rules relating to hypernyms and attributes. We introduce two key novelties for improved learning: (1) enforcement of rules for a group instead of a single concept to take into account class-wise relationships, and (2) confidence margins inside logical operators that enable implicit curriculum learning and prevent premature overfitting. We evaluate the advantages of incorporating each knowledge source and show consistent gains over prior state-of-art methods in both conventional and generalized ZSL e.g. 11.5%, 5.5%, and 11.6% improvements on AWA2, CUB, and Kinetics respectively.
