Semantically Consistent Regularization for Zero-Shot Recognition
Semantically Consistent Regularization for Zero-Shot Recognition
复制标题
DOI：
10.1109/cvpr.2017.220
复制
发表时间：
2017-04
期刊：
影响因子：
--
通讯作者：
Pedro Morgado;N. Vasconcelos
中科院分区：
文献类型：
--
作者：
Pedro Morgado;N. Vasconcelos
考虑了语义在零样本学习中的作用。根据所提供的监督形式来分析以前方法的有效性。虽然有些人独立学习语义，但其他人只监督训练类解释的语义子空间。因此，前者能够约束整个空间，但缺乏对语义相关性进行建模的能力。后者解决了这个问题，但留下了部分语义空间不受监督。这种互补性在新的卷积神经网络（CNN）框架中得到了利用，该框架提出使用语义作为识别的约束。尽管经过分类训练的 CNN 没有迁移能力，但可以通过学习隐藏语义层和用于分类的语义代码来鼓励这种能力。然后引入两种形式的语义约束。第一个是基于损失的正则化器，它在每个语义预测器上引入泛化约束。第二个是码字正则化器，它支持与先前语义知识一致的语义到类映射，同时允许从数据中学习这些知识。在多个数据集上实现了对最先进技术的显着改进。
The role of semantics in zero-shot learning is considered. The effectiveness of previous approaches is analyzed according to the form of supervision provided. While some learn semantics independently, others only supervise the semantic subspace explained by training classes. Thus, the former is able to constrain the whole space but lacks the ability to model semantic correlations. The latter addresses this issue but leaves part of the semantic space unsupervised. This complementarity is exploited in a new convolutional neural network (CNN) framework, which proposes the use of semantics as constraints for recognition. Although a CNN trained for classification has no transfer ability, this can be encouraged by learning an hidden semantic layer together with a semantic code for classification. Two forms of semantic constraints are then introduced. The first is a loss-based regularizer that introduces a generalization constraint on each semantic predictor. The second is a codeword regularizer that favors semantic-to-class mappings consistent with prior semantic knowledge while allowing these to be learned from data. Significant improvements over the state-of-the-art are achieved on several datasets.