Multi-Granularity Mutual Refinement Network for Zero-Shot Learning

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Wang, Ning, Yu, Long, Hua, Cong, Zhu, Guangming, Mei, Lin, Shah, Syed Afaq Ali, Bennamoun, Mohammed, Zhang, Liang
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866908644275126272
author Wang, Ning
Yu, Long
Hua, Cong
Zhu, Guangming
Mei, Lin
Shah, Syed Afaq Ali
Bennamoun, Mohammed
Zhang, Liang
author_facet Wang, Ning
Yu, Long
Hua, Cong
Zhu, Guangming
Mei, Lin
Shah, Syed Afaq Ali
Bennamoun, Mohammed
Zhang, Liang
contents Zero-shot learning (ZSL) aims to recognize unseen classes with zero samples by transferring semantic knowledge from seen classes. Current approaches typically correlate global visual features with semantic information (i.e., attributes) or align local visual region features with corresponding attributes to enhance visual-semantic interactions. Although effective, these methods often overlook the intrinsic interactions between local region features, which can further improve the acquisition of transferable and explicit visual features. In this paper, we propose a network named Multi-Granularity Mutual Refinement Network (Mg-MRN), which refine discriminative and transferable visual features by learning decoupled multi-granularity features and cross-granularity feature interactions. Specifically, we design a multi-granularity feature extraction module to learn region-level discriminative features through decoupled region feature mining. Then, a cross-granularity feature fusion module strengthens the inherent interactions between region features of varying granularities. This module enhances the discriminability of representations at each granularity level by integrating region representations from adjacent hierarchies, further improving ZSL recognition performance. Extensive experiments on three popular ZSL benchmark datasets demonstrate the superiority and competitiveness of our proposed Mg-MRN method. Our code is available at https://github.com/NingWang2049/Mg-MRN.
format Preprint
id arxiv_https___arxiv_org_abs_2511_08163
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Multi-Granularity Mutual Refinement Network for Zero-Shot Learning
Wang, Ning
Yu, Long
Hua, Cong
Zhu, Guangming
Mei, Lin
Shah, Syed Afaq Ali
Bennamoun, Mohammed
Zhang, Liang
Computer Vision and Pattern Recognition
Zero-shot learning (ZSL) aims to recognize unseen classes with zero samples by transferring semantic knowledge from seen classes. Current approaches typically correlate global visual features with semantic information (i.e., attributes) or align local visual region features with corresponding attributes to enhance visual-semantic interactions. Although effective, these methods often overlook the intrinsic interactions between local region features, which can further improve the acquisition of transferable and explicit visual features. In this paper, we propose a network named Multi-Granularity Mutual Refinement Network (Mg-MRN), which refine discriminative and transferable visual features by learning decoupled multi-granularity features and cross-granularity feature interactions. Specifically, we design a multi-granularity feature extraction module to learn region-level discriminative features through decoupled region feature mining. Then, a cross-granularity feature fusion module strengthens the inherent interactions between region features of varying granularities. This module enhances the discriminability of representations at each granularity level by integrating region representations from adjacent hierarchies, further improving ZSL recognition performance. Extensive experiments on three popular ZSL benchmark datasets demonstrate the superiority and competitiveness of our proposed Mg-MRN method. Our code is available at https://github.com/NingWang2049/Mg-MRN.
title Multi-Granularity Mutual Refinement Network for Zero-Shot Learning
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2511.08163