MA-AVT: Modality Alignment for Parameter-Efficient Audio-Visual Transformers

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Mahmud, Tanvir, Mo, Shentong, Tian, Yapeng, Marculescu, Diana
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916279593467904
author Mahmud, Tanvir
Mo, Shentong
Tian, Yapeng
Marculescu, Diana
author_facet Mahmud, Tanvir
Mo, Shentong
Tian, Yapeng
Marculescu, Diana
contents Recent advances in pre-trained vision transformers have shown promise in parameter-efficient audio-visual learning without audio pre-training. However, few studies have investigated effective methods for aligning multimodal features in parameter-efficient audio-visual transformers. In this paper, we propose MA-AVT, a new parameter-efficient audio-visual transformer employing deep modality alignment for corresponding multimodal semantic features. Specifically, we introduce joint unimodal and multimodal token learning for aligning the two modalities with a frozen modality-shared transformer. This allows the model to learn separate representations for each modality, while also attending to the cross-modal relationships between them. In addition, unlike prior work that only aligns coarse features from the output of unimodal encoders, we introduce blockwise contrastive learning to align coarse-to-fine-grain hierarchical features throughout the encoding phase. Furthermore, to suppress the background features in each modality from foreground matched audio-visual features, we introduce a robust discriminative foreground mining scheme. Through extensive experiments on benchmark AVE, VGGSound, and CREMA-D datasets, we achieve considerable performance improvements over SOTA methods.
format Preprint
id arxiv_https___arxiv_org_abs_2406_04930
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle MA-AVT: Modality Alignment for Parameter-Efficient Audio-Visual Transformers
Mahmud, Tanvir
Mo, Shentong
Tian, Yapeng
Marculescu, Diana
Computer Vision and Pattern Recognition
Multimedia
Sound
Audio and Speech Processing
Recent advances in pre-trained vision transformers have shown promise in parameter-efficient audio-visual learning without audio pre-training. However, few studies have investigated effective methods for aligning multimodal features in parameter-efficient audio-visual transformers. In this paper, we propose MA-AVT, a new parameter-efficient audio-visual transformer employing deep modality alignment for corresponding multimodal semantic features. Specifically, we introduce joint unimodal and multimodal token learning for aligning the two modalities with a frozen modality-shared transformer. This allows the model to learn separate representations for each modality, while also attending to the cross-modal relationships between them. In addition, unlike prior work that only aligns coarse features from the output of unimodal encoders, we introduce blockwise contrastive learning to align coarse-to-fine-grain hierarchical features throughout the encoding phase. Furthermore, to suppress the background features in each modality from foreground matched audio-visual features, we introduce a robust discriminative foreground mining scheme. Through extensive experiments on benchmark AVE, VGGSound, and CREMA-D datasets, we achieve considerable performance improvements over SOTA methods.
title MA-AVT: Modality Alignment for Parameter-Efficient Audio-Visual Transformers
topic Computer Vision and Pattern Recognition
Multimedia
Sound
Audio and Speech Processing
url https://arxiv.org/abs/2406.04930