Rethinking attribute localization for zero-shot learning  

作　　者：Shuhuang CHEN Shiming CHEN Guo-Sen XIE Xiangbo SHU Xinge YOU Xuelong LI 

机构地区：[1]School of Electronic Information and Communication,Huazhong University of Science and Technology,Wuhan 430074,China [2]School of Computer Science and Engineering,Nanjing University of Science and Technology,Nanjing 210094,China [3]School of Artificial Intelligence,Optics and Electronics,Northwestern Polytechnical University,Xi’an 710072,China

出　　处：《Science China(Information Sciences)》2024年第7期180-192,共13页中国科学（信息科学）（英文版）

基　　金：supported by National Key R&D Program of China(Grant No.2022YFC3301000)。

摘　　要：Recent advancements in attribute localization have showcased its potential in discovering the intrinsic semantic knowledge for visual feature representations,thereby facilitating significant visual-semantic interactions essential for zero-shot learning(ZSL).However,the majority of existing attribute localization methods heavily rely on classification constraints,resulting in accurate localization of only a few attributes while neglecting the rest important attributes associated with other classes.This limitation hinders the discovery of the intrinsic semantic relationships between attributes and visual features across all classes.To address this problem,we propose a novel attribute localization refinement(ALR)module designed to enhance the model’s ability to accurately localize all attributes.Essentially,we enhance weak discriminant attributes by grouping them and introduce weighted attribute regression to standardize the mapping values of semantic attributes.This module can be flexibly combined with existing attribute localization methods.Our experiments show that when combined with the ALR module,the localization errors in existing methods are corrected,and state-of-the-art classification performance is achieved.

关 键 词：zero-shot learning attention mechanism attribute localization image classification 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程] TP391.41[自动化与计算机技术—控制科学与工程]