A Biologically Inspired Feature Enhancement Framework for Zero-Shot Learning

Most of the Zero-Shot Learning (ZSL) algorithms currently use pre-Trained models as their feature extractors, which are usually trained on ImageNet by using deep neural networks. The richness of the feature information embedded in the pre-Trained models can help the ZSL model extract more useful features from its limited training data. However, sometimes the difference between the training data of the current ZSL task and the ImageNet is too large, which may cause the use of pre-Trained models has no obvious help or even negative impact on the model performance. To solve this problem, this paper proposes a biologically inspired feature enhancement framework for ZSL. Specifically, we design a dual-channel learning framework that uses auxiliary data sets to enhance the feature extractor of the ZSL model and propose a novel method to guide the selection of the auxiliary data sets based on the knowledge of biological taxonomy. Extensive experimental results show that our proposed method can effectively improve the generalization ability of the ZSL model and achieve state-of-The-Art results on three benchmark ZSL tasks. We also explained the experimental phenomena through the way of feature visualization.