CVAIMMFeb 22, 2025

Audio Visual Segmentation Through Text Embeddings

arXiv:2502.16359v2h-index: 11Has CodeICIP
Originality Incremental advance
AI Analysis

This work addresses data scarcity in audio-visual segmentation for video analysis, offering an incremental improvement by leveraging cross-modal semantic alignment.

The paper tackles the problem of audio-visual segmentation with limited data by proposing AV2T-SAM, a framework that bridges audio features with text embeddings in a pre-trained model to enhance audio-visual alignment, achieving improved performance on the AVSBench dataset.

The goal of Audio-Visual Segmentation (AVS) is to localize and segment the sounding source objects from video frames. Research on AVS suffers from data scarcity due to the high cost of fine-grained manual annotations. Recent works attempt to overcome the challenge of limited data by leveraging the vision foundation model, Segment Anything Model (SAM), prompting it with audio to enhance its ability to segment sounding source objects. While this approach alleviates the model's burden on understanding visual modality by utilizing knowledge of pre-trained SAM, it does not address the fundamental challenge of learning audio-visual correspondence with limited data. To address this limitation, we propose \textbf{AV2T-SAM}, a novel framework that bridges audio features with the text embedding space of pre-trained text-prompted SAM. Our method leverages multimodal correspondence learned from rich text-image paired datasets to enhance audio-visual alignment. Furthermore, we introduce a novel feature, $\mathbf{\textit{\textbf{f}}_{CLIP} \odot \textit{\textbf{f}}_{CLAP}}$, which emphasizes shared semantics of audio and visual modalities while filtering irrelevant noise. Our approach outperforms existing methods on the AVSBench dataset by effectively utilizing pre-trained segmentation models and cross-modal semantic alignment. The source code is released at https://github.com/bok-bok/AV2T-SAM.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes