Anchor-aware Deep Metric Learning for Audio-visual Retrieval

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zeng, Donghuo, Wang, Yanan, Ikeda, Kazushi, Yu, Yi
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913324662259712
author Zeng, Donghuo
Wang, Yanan
Ikeda, Kazushi
Yu, Yi
author_facet Zeng, Donghuo
Wang, Yanan
Ikeda, Kazushi
Yu, Yi
contents Metric learning minimizes the gap between similar (positive) pairs of data points and increases the separation of dissimilar (negative) pairs, aiming at capturing the underlying data structure and enhancing the performance of tasks like audio-visual cross-modal retrieval (AV-CMR). Recent works employ sampling methods to select impactful data points from the embedding space during training. However, the model training fails to fully explore the space due to the scarcity of training data points, resulting in an incomplete representation of the overall positive and negative distributions. In this paper, we propose an innovative Anchor-aware Deep Metric Learning (AADML) method to address this challenge by uncovering the underlying correlations among existing data points, which enhances the quality of the shared embedding space. Specifically, our method establishes a correlation graph-based manifold structure by considering the dependencies between each sample as the anchor and its semantically similar samples. Through dynamic weighting of the correlations within this underlying manifold structure using an attention-driven mechanism, Anchor Awareness (AA) scores are obtained for each anchor. These AA scores serve as data proxies to compute relative distances in metric learning approaches. Extensive experiments conducted on two audio-visual benchmark datasets demonstrate the effectiveness of our proposed AADML method, significantly surpassing state-of-the-art models. Furthermore, we investigate the integration of AA proxies with various metric learning methods, further highlighting the efficacy of our approach.
format Preprint
id arxiv_https___arxiv_org_abs_2404_13789
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Anchor-aware Deep Metric Learning for Audio-visual Retrieval
Zeng, Donghuo
Wang, Yanan
Ikeda, Kazushi
Yu, Yi
Sound
Artificial Intelligence
Information Retrieval
Multimedia
Audio and Speech Processing
Metric learning minimizes the gap between similar (positive) pairs of data points and increases the separation of dissimilar (negative) pairs, aiming at capturing the underlying data structure and enhancing the performance of tasks like audio-visual cross-modal retrieval (AV-CMR). Recent works employ sampling methods to select impactful data points from the embedding space during training. However, the model training fails to fully explore the space due to the scarcity of training data points, resulting in an incomplete representation of the overall positive and negative distributions. In this paper, we propose an innovative Anchor-aware Deep Metric Learning (AADML) method to address this challenge by uncovering the underlying correlations among existing data points, which enhances the quality of the shared embedding space. Specifically, our method establishes a correlation graph-based manifold structure by considering the dependencies between each sample as the anchor and its semantically similar samples. Through dynamic weighting of the correlations within this underlying manifold structure using an attention-driven mechanism, Anchor Awareness (AA) scores are obtained for each anchor. These AA scores serve as data proxies to compute relative distances in metric learning approaches. Extensive experiments conducted on two audio-visual benchmark datasets demonstrate the effectiveness of our proposed AADML method, significantly surpassing state-of-the-art models. Furthermore, we investigate the integration of AA proxies with various metric learning methods, further highlighting the efficacy of our approach.
title Anchor-aware Deep Metric Learning for Audio-visual Retrieval
topic Sound
Artificial Intelligence
Information Retrieval
Multimedia
Audio and Speech Processing
url https://arxiv.org/abs/2404.13789