基于间接域适应特征生成的直推式零样本学习方法
作者:
作者单位:

作者简介:

黄晟(1988-),男,博士,副教授,博士生导师,CCF专业会员,主要研究领域为模式识别,机器学习,计算机视觉;张小洪(1973-),男,博士,教授,博士生导师,CCF专业会员,主要研究领域为图像处理,机器学习,模式识别,数据挖掘,智能软件工程;杨万里(1996-),男,硕士生,主要研究领域为计算机视觉;杨丹(1962-),男,博士,教授,博士生导师,主要研究领域为模式识别,图像处理,软件工程,智能制造;张译(1994-),男,博士生,主要研究领域为计算机视觉,深度学习.

通讯作者:

黄晟Email:huangsheng@cqu.edu.cn

中图分类号:

TP181

基金项目:

国家重点研发计划(2018YFB2101200);国家自然科学基金(61772093,61602068);中央高校基本科研业务费专项资金(2019CDYGYB014)


Feature Generation Approach with Indirect Domain Adaptation for Transductive Zero-shot Learning
Author:
Affiliation:

Fund Project:

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
  • 资源附件
  • |
  • 文章评论
    摘要:

    近年来,零样本学习备受机器学习和计算机视觉领域的关注.传统的归纳式零样本学习方法通过建立语义与视觉之间的映射关系,实现类别之间的知识迁移.这类方法存在着可见类和未见类之间的映射域漂移(projection domain shift)问题,直推式零样本学习方法通过在训练阶段引入无标定的未见类数据进行域适应,能够有效地缓解上述问题并提升零样本学习精度.然而,通过实验分析发现,这种直接在视觉空间同时进行语义映射建立和域适应的直推式零样本学习方法容易陷入“相互制衡”问题,从而无法充分发挥语义映射和域适应的最佳性能.针对上述问题,提出了一种基于间接域适应特征生成(feature generation with indirect domain adaptation,FG-IDA)的直推式零样本学习方法.该方法通过串行化语义映射和域适应优化过程,使得直推式零样本学习的这两大核心步骤能够在不同特征空间分别进行最佳优化,从而激发其潜能提升零样本识别精度.在4个标准数据集(CUB,AWA1,AWA2,SUN)上对FG-IDA模型进行了评估,实验结果表明,FG-IDA模型不仅展示出了相对其他直推学习方法的优越性,同时还在AWA1,AWA2和CUB数据集上取得了当前最优结果(the state-of-the-art performance).此外还进行了详尽的消融实验,通过与直接域适应方法进行对比分析,验证了直推式零样本学习中的“相互制衡”问题以及间接域适应思想的先进性.

    Abstract:

    In recent years, zero-shot learning has attracted extensive attention in machine learning and computer vision. The conventional inductive zero-shot learning attempts to establish the mappings between semantic and visual features for transferring the knowledge between classes. However, such approaches suffer from the projection domain shift between the seen and unseen classes. The transductive zero-shot learning is proposed to alleviate this issue by leveraging the unlabeled unseen data for domain adaptation in the training stage. Unfortunately, empirically study finds that these transductive zero-shot learning approaches, which optimize the semantic mapping and domain adaption in visual feature space simultaneously, are easy to trap in "mutual restriction", and thereby limit the potentials of both these two steps. In order to address the aforementioned issue, a novel transductive zero-shot learning approach named feature generation with indirect domain adaption (FG-IDA) is proposed, that conducts the semantic mapping and domain adaption orderly and optimizes these two steps in different spaces separately for inspiring their performance potentials and further improving the zero-shot recognition accuracy. FG-IDA is evaluated on four benchmarks, namely CUB, AWA1, AWA2, and SUN. The experimental results demonstrate the superiority of the proposed method over other transductive zero-shot learning approaches, and also show that FG-IDA achieves the state-of-the-art performances on CUB, AWA1, and AWA2 datasets. Moreover, the detailed ablation analysis is conducted and the results empirically prove the existence of the "mutual restriction" effect in direct domain adaption-based transductive zero-shot learning approaches and the effectiveness of the indirect domain adaption idea.

    参考文献
    相似文献
    引证文献
引用本文

黄晟,杨万里,张译,张小洪,杨丹.基于间接域适应特征生成的直推式零样本学习方法.软件学报,2022,33(11):4268-4284

复制
分享
文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 收稿日期:2020-12-16
  • 最后修改日期:2021-01-25
  • 录用日期:
  • 在线发布日期: 2022-11-11
  • 出版日期: 2022-11-06
您是第位访问者
版权所有:中国科学院软件研究所 京ICP备05046678号-3
地址:北京市海淀区中关村南四街4号,邮政编码:100190
电话:010-62562563 传真:010-62562533 Email:jos@iscas.ac.cn
技术支持:北京勤云科技发展有限公司

京公网安备 11040202500063号