# Which One Is Sounding? Binaural Sounding Instance Disambiguation for Audio-Visual Segmentation

**Authors:** Haoze Ma, Yidi Li, Yu Ma, Pengyuan Zhao, Yi Shi, Bin Ren, Yanwen Guo, Dimitrios Kanoulas  
**Lab:** Taiyuan University of Technology · **Published:** 4 Nov 2026  
**Links:** [arXiv](https://arxiv.org/abs/2611.06074) · [PDF](https://arxiv.org/pdf/2611.06074) · [This page](https://omen-bit.github.io/ai-paper-daily/paper/2611.06074.html)

## Key numbers

- **41.21**: improving instance-level mIoU by 35.19 and 41.21 percentage points

## Abstract

Existing audio-visual segmentation methods mainly predict sound-related regions or category masks and often fail to identify the sounding instance when multiple same-class candidates coexist. Recent audio-visual instance segmentation methods address instance-level prediction but rely largely on motion and cross-frame association, which may become unreliable under sparse observations or inconspicuous motion. To this end, we introduce binaural audio, whose interaural differences encode source-direction information, to provide spatial constraints for distinguishing the sounding instance among same-class visual candidates. We propose Binaural Sounding Instance Disambiguation for Audio-Visual Segmentation (BiSID-AVS), which progressively refines category-level candidate responses into a mask of the true sounding instance. BiSID-AVS first grounds category-consistent candidate regions through audio prompting, then projects binaural cues into an image-plane spatial response map, and finally refines the true sounding instance through dual-level spatial conditioning at the feature and decoder levels. Experiments on the binaurally extended AVS-Synthetic benchmark and Habitat-AVS dataset for robotic indoor perception show that BiSID-AVS achieves the best performance on the multi-candidate subsets, improving instance-level mIoU by 35.19 and 41.21 percentage points, respectively, while substantially reducing false activation on non-sounding same-class regions.

---

Notes written by AI from the paper, numbers copied from the abstract. Check the paper before you rely on them. From AI Papers Daily.