TAViS: Text-bridged Audio-Visual Segmentation with Foundation Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Luo, Ziyang, Liu, Nian, Yang, Xuguang, Khan, Salman, Anwer, Rao Muhammad, Cholakkal, Hisham, Khan, Fahad Shahbaz, Han, Junwei
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917135621554176
author Luo, Ziyang
Liu, Nian
Yang, Xuguang
Khan, Salman
Anwer, Rao Muhammad
Cholakkal, Hisham
Khan, Fahad Shahbaz
Han, Junwei
author_facet Luo, Ziyang
Liu, Nian
Yang, Xuguang
Khan, Salman
Anwer, Rao Muhammad
Cholakkal, Hisham
Khan, Fahad Shahbaz
Han, Junwei
contents Audio-Visual Segmentation (AVS) faces a fundamental challenge of effectively aligning audio and visual modalities. While recent approaches leverage foundation models to address data scarcity, they often rely on single-modality knowledge or combine foundation models in an off-the-shelf manner, failing to address the cross-modal alignment challenge. In this paper, we present TAViS, a novel framework that \textbf{couples} the knowledge of multimodal foundation models (ImageBind) for cross-modal alignment and a segmentation foundation model (SAM2) for precise segmentation. However, effectively combining these models poses two key challenges: the difficulty in transferring the knowledge between SAM2 and ImageBind due to their different feature spaces, and the insufficiency of using only segmentation loss for supervision. To address these challenges, we introduce a text-bridged design with two key components: (1) a text-bridged hybrid prompting mechanism where pseudo text provides class prototype information while retaining modality-specific details from both audio and visual inputs, and (2) an alignment supervision strategy that leverages text as a bridge to align shared semantic concepts within audio-visual modalities. Our approach achieves superior performance on single-source, multi-source, semantic datasets, and excels in zero-shot settings.
format Preprint
id arxiv_https___arxiv_org_abs_2506_11436
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle TAViS: Text-bridged Audio-Visual Segmentation with Foundation Models
Luo, Ziyang
Liu, Nian
Yang, Xuguang
Khan, Salman
Anwer, Rao Muhammad
Cholakkal, Hisham
Khan, Fahad Shahbaz
Han, Junwei
Computer Vision and Pattern Recognition
Audio-Visual Segmentation (AVS) faces a fundamental challenge of effectively aligning audio and visual modalities. While recent approaches leverage foundation models to address data scarcity, they often rely on single-modality knowledge or combine foundation models in an off-the-shelf manner, failing to address the cross-modal alignment challenge. In this paper, we present TAViS, a novel framework that \textbf{couples} the knowledge of multimodal foundation models (ImageBind) for cross-modal alignment and a segmentation foundation model (SAM2) for precise segmentation. However, effectively combining these models poses two key challenges: the difficulty in transferring the knowledge between SAM2 and ImageBind due to their different feature spaces, and the insufficiency of using only segmentation loss for supervision. To address these challenges, we introduce a text-bridged design with two key components: (1) a text-bridged hybrid prompting mechanism where pseudo text provides class prototype information while retaining modality-specific details from both audio and visual inputs, and (2) an alignment supervision strategy that leverages text as a bridge to align shared semantic concepts within audio-visual modalities. Our approach achieves superior performance on single-source, multi-source, semantic datasets, and excels in zero-shot settings.
title TAViS: Text-bridged Audio-Visual Segmentation with Foundation Models
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2506.11436