Audit After Segmentation: Reference-Free Mask Quality Assessment for Language-Referred Audio-Visual Segmentation
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912874630217728 |
|---|---|
| author | Zhou, Jinxing Zhou, Yanghao Wang, Yaoting Han, Zongyan Ma, Jiaqi Ding, Henghui Anwer, Rao Muhammad Cholakkal, Hisham |
| author_facet | Zhou, Jinxing Zhou, Yanghao Wang, Yaoting Han, Zongyan Ma, Jiaqi Ding, Henghui Anwer, Rao Muhammad Cholakkal, Hisham |
| contents | Language-referred audio-visual segmentation (Ref-AVS) aims to segment target objects described by natural language by jointly reasoning over video, audio, and text. Beyond generating segmentation masks, providing rich and interpretable diagnoses of mask quality remains largely underexplored. In this work, we introduce Mask Quality Assessment in the Ref-AVS context (MQA-RefAVS), a new task that evaluates the quality of candidate segmentation masks without relying on ground-truth annotations as references at inference time. Given audio-visual-language inputs and each provided segmentation mask, the task requires estimating its IoU with the unobserved ground truth, identifying the corresponding error type, and recommending an actionable quality-control decision. To support this task, we construct MQ-RAVSBench, a benchmark featuring diverse and representative mask error modes that span both geometric and semantic issues. We further propose MQ-Auditor, a multimodal large language model (MLLM)-based auditor that explicitly reasons over multimodal cues and mask information to produce quantitative and qualitative mask quality assessments. Extensive experiments demonstrate that MQ-Auditor outperforms strong open-source and commercial MLLMs and can be integrated with existing Ref-AVS systems to detect segmentation failures and support downstream segmentation improvement. Data and codes will be released at https://github.com/jasongief/MQA-RefAVS. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_03892 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Audit After Segmentation: Reference-Free Mask Quality Assessment for Language-Referred Audio-Visual Segmentation Zhou, Jinxing Zhou, Yanghao Wang, Yaoting Han, Zongyan Ma, Jiaqi Ding, Henghui Anwer, Rao Muhammad Cholakkal, Hisham Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning Multimedia Sound Audio and Speech Processing Language-referred audio-visual segmentation (Ref-AVS) aims to segment target objects described by natural language by jointly reasoning over video, audio, and text. Beyond generating segmentation masks, providing rich and interpretable diagnoses of mask quality remains largely underexplored. In this work, we introduce Mask Quality Assessment in the Ref-AVS context (MQA-RefAVS), a new task that evaluates the quality of candidate segmentation masks without relying on ground-truth annotations as references at inference time. Given audio-visual-language inputs and each provided segmentation mask, the task requires estimating its IoU with the unobserved ground truth, identifying the corresponding error type, and recommending an actionable quality-control decision. To support this task, we construct MQ-RAVSBench, a benchmark featuring diverse and representative mask error modes that span both geometric and semantic issues. We further propose MQ-Auditor, a multimodal large language model (MLLM)-based auditor that explicitly reasons over multimodal cues and mask information to produce quantitative and qualitative mask quality assessments. Extensive experiments demonstrate that MQ-Auditor outperforms strong open-source and commercial MLLMs and can be integrated with existing Ref-AVS systems to detect segmentation failures and support downstream segmentation improvement. Data and codes will be released at https://github.com/jasongief/MQA-RefAVS. |
| title | Audit After Segmentation: Reference-Free Mask Quality Assessment for Language-Referred Audio-Visual Segmentation |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning Multimedia Sound Audio and Speech Processing |
| url | https://arxiv.org/abs/2602.03892 |