Aligning enhanced feature representation for generalized zero-shot learning  

作　　者：Zhiyu FANG Xiaobin ZHU Chun YANG Hongyang ZHOU Jingyan QIN Xu-Cheng YIN 

机构地区：[1]School of Computer&Communication Engineering,University of Science and Technology Beijing,Beijing 100083,China

出　　处：《Science China(Information Sciences)》2025年第2期70-84,共15页中国科学(信息科学)(英文版)

基　　金：supported by National Science and Technology Major Project(Grant No.2020AAA0109701);National Science Fund for Distinguished Young Scholars(Grant No.62125601);National Natural Science Foundation of China(Grant No.62076024)。

摘　　要：Constructing an effective common latent embedding by aligning the latent spaces of cross-modal variational autoencoders(VAEs)is a popular strategy for generalized zero-shot learning(GZSL).However,due to the lack of fine-grained instance-wise annotations,existing VAE methods can easily suffer from the posterior collapse problem.In this paper,we propose an innovative asymmetric VAE network by aligning enhanced feature representation(AEFR)for GZSL.Distinguished from general VAE structures,we designed two asymmetric encoders for visual and semantic observations and one decoder for visual reconstruction.Specifically,we propose a simple yet effective gated attention mechanism(GAM)in the visual encoder for enhancing the information interaction between observations and latent variables,alleviating the possible posterior collapse problem effectively.In addition,we propose a novel distributional decoupling-based contrastive learning(D^(2)-CL)to guide learning classification-relevant information while aligning the representations at the taxonomy level in the latent representation space.Extensive experiments on publicly available datasets demonstrate the state-of-the-art performance of our method.The source code is available at https://github.com/seeyourmind/AEFR.

关 键 词：generalized zero-shot learning gated attention mechanism contrastive learning multi-modal alignment 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]