Dynamic Derivation and Elimination: Audio Visual Segmentation with Enhanced Audio Semantics

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Liu, Chen, Yang, Liying, Li, Peike, Wang, Dadong, Li, Lincheng, Yu, Xin
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913740367069184
author Liu, Chen
Yang, Liying
Li, Peike
Wang, Dadong
Li, Lincheng
Yu, Xin
author_facet Liu, Chen
Yang, Liying
Li, Peike
Wang, Dadong
Li, Lincheng
Yu, Xin
contents Sound-guided object segmentation has drawn considerable attention for its potential to enhance multimodal perception. Previous methods primarily focus on developing advanced architectures to facilitate effective audio-visual interactions, without fully addressing the inherent challenges posed by audio natures, \emph{\ie}, (1) feature confusion due to the overlapping nature of audio signals, and (2) audio-visual matching difficulty from the varied sounds produced by the same object. To address these challenges, we propose Dynamic Derivation and Elimination (DDESeg): a novel audio-visual segmentation framework. Specifically, to mitigate feature confusion, DDESeg reconstructs the semantic content of the mixed audio signal by enriching the distinct semantic information of each individual source, deriving representations that preserve the unique characteristics of each sound. To reduce the matching difficulty, we introduce a discriminative feature learning module, which enhances the semantic distinctiveness of generated audio representations. Considering that not all derived audio representations directly correspond to visual features (e.g., off-screen sounds), we propose a dynamic elimination module to filter out non-matching elements. This module facilitates targeted interaction between sounding regions and relevant audio semantics. By scoring the interacted features, we identify and filter out irrelevant audio information, ensuring accurate audio-visual alignment. Comprehensive experiments demonstrate that our framework achieves superior performance in AVS datasets.
format Preprint
id arxiv_https___arxiv_org_abs_2503_12840
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Dynamic Derivation and Elimination: Audio Visual Segmentation with Enhanced Audio Semantics
Liu, Chen
Yang, Liying
Li, Peike
Wang, Dadong
Li, Lincheng
Yu, Xin
Sound
Computer Vision and Pattern Recognition
Audio and Speech Processing
Sound-guided object segmentation has drawn considerable attention for its potential to enhance multimodal perception. Previous methods primarily focus on developing advanced architectures to facilitate effective audio-visual interactions, without fully addressing the inherent challenges posed by audio natures, \emph{\ie}, (1) feature confusion due to the overlapping nature of audio signals, and (2) audio-visual matching difficulty from the varied sounds produced by the same object. To address these challenges, we propose Dynamic Derivation and Elimination (DDESeg): a novel audio-visual segmentation framework. Specifically, to mitigate feature confusion, DDESeg reconstructs the semantic content of the mixed audio signal by enriching the distinct semantic information of each individual source, deriving representations that preserve the unique characteristics of each sound. To reduce the matching difficulty, we introduce a discriminative feature learning module, which enhances the semantic distinctiveness of generated audio representations. Considering that not all derived audio representations directly correspond to visual features (e.g., off-screen sounds), we propose a dynamic elimination module to filter out non-matching elements. This module facilitates targeted interaction between sounding regions and relevant audio semantics. By scoring the interacted features, we identify and filter out irrelevant audio information, ensuring accurate audio-visual alignment. Comprehensive experiments demonstrate that our framework achieves superior performance in AVS datasets.
title Dynamic Derivation and Elimination: Audio Visual Segmentation with Enhanced Audio Semantics
topic Sound
Computer Vision and Pattern Recognition
Audio and Speech Processing
url https://arxiv.org/abs/2503.12840