Discrepancy-Aware Attention Network for Enhanced Audio-Visual Zero-Shot Learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yu, RunLin, Gong, Yipu, Li, Wenrui, Sun, Aiwen, Zheng, Mengren
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929633030569984
author Yu, RunLin
Gong, Yipu
Li, Wenrui
Sun, Aiwen
Zheng, Mengren
author_facet Yu, RunLin
Gong, Yipu
Li, Wenrui
Sun, Aiwen
Zheng, Mengren
contents Audio-visual Zero-Shot Learning (ZSL) has attracted significant attention for its ability to identify unseen classes and perform well in video classification tasks. However, modal imbalance in (G)ZSL leads to over-reliance on the optimal modality, reducing discriminative capabilities for unseen classes. Some studies have attempted to address this issue by modifying parameter gradients, but two challenges still remain: (a) Quality discrepancies, where modalities offer differing quantities and qualities of information for the same concept. (b) Content discrepancies, where sample contributions within a modality vary significantly. To address these challenges, we propose a Discrepancy-Aware Attention Network (DAAN) for Enhanced Audio-Visual ZSL. Our approach introduces a Quality-Discrepancy Mitigation Attention (QDMA) unit to minimize redundant information in the high-quality modality and a Contrastive Sample-level Gradient Modulation (CSGM) block to adjust gradient magnitudes and balance content discrepancies. We quantify modality contributions by integrating optimization and convergence rate for more precise gradient modulation in CSGM. Experiments demonstrates DAAN achieves state-of-the-art performance on benchmark datasets, with ablation studies validating the effectiveness of individual modules.
format Preprint
id arxiv_https___arxiv_org_abs_2412_11715
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Discrepancy-Aware Attention Network for Enhanced Audio-Visual Zero-Shot Learning
Yu, RunLin
Gong, Yipu
Li, Wenrui
Sun, Aiwen
Zheng, Mengren
Computer Vision and Pattern Recognition
Multimedia
Sound
Audio and Speech Processing
Audio-visual Zero-Shot Learning (ZSL) has attracted significant attention for its ability to identify unseen classes and perform well in video classification tasks. However, modal imbalance in (G)ZSL leads to over-reliance on the optimal modality, reducing discriminative capabilities for unseen classes. Some studies have attempted to address this issue by modifying parameter gradients, but two challenges still remain: (a) Quality discrepancies, where modalities offer differing quantities and qualities of information for the same concept. (b) Content discrepancies, where sample contributions within a modality vary significantly. To address these challenges, we propose a Discrepancy-Aware Attention Network (DAAN) for Enhanced Audio-Visual ZSL. Our approach introduces a Quality-Discrepancy Mitigation Attention (QDMA) unit to minimize redundant information in the high-quality modality and a Contrastive Sample-level Gradient Modulation (CSGM) block to adjust gradient magnitudes and balance content discrepancies. We quantify modality contributions by integrating optimization and convergence rate for more precise gradient modulation in CSGM. Experiments demonstrates DAAN achieves state-of-the-art performance on benchmark datasets, with ablation studies validating the effectiveness of individual modules.
title Discrepancy-Aware Attention Network for Enhanced Audio-Visual Zero-Shot Learning
topic Computer Vision and Pattern Recognition
Multimedia
Sound
Audio and Speech Processing
url https://arxiv.org/abs/2412.11715