A Biologically Inspired Feature Enhancement Framework for Zero-Shot Learning

TL;DR

This paper introduces a biologically inspired dual-channel framework that enhances feature extraction in zero-shot learning, improving generalization and achieving state-of-the-art results by leveraging auxiliary datasets guided by biological taxonomy.

Contribution

It proposes a novel dual-channel learning framework with a biologically inspired method for selecting auxiliary datasets to improve ZSL performance.

Findings

Enhanced ZSL generalization ability

Achieved state-of-the-art results on benchmarks

Feature visualization supports effectiveness

Abstract

Most of the Zero-Shot Learning (ZSL) algorithms currently use pre-trained models as their feature extractors, which are usually trained on the ImageNet data set 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 samples. However, sometimes the difference between the training data set of the current ZSL task and the ImageNet data set is too large, which may lead to the use of pre-trained models has no obvious help or even negative impact on the performance of the ZSL model. 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.