# PRIMED: Adaptive Modality Suppression for Referring Audio-Visual Segmentation via Biased Competition

arXiv: https://arxiv.org/abs/2605.07154 · HTML: https://mlsanity.com/paper/2605.07154/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 29 of its 38 references that are in the map.
- First posted on arXiv 8 May 2026.

## Builds on (most cited first, 29 of 29)

- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter](https://mlsanity.com/paper/1910.01108/) (2019)
- [Qwen3-Omni Technical Report](https://mlsanity.com/paper/2509.17765/) (2025)
- [Hiera: A Hierarchical Vision Transformer without the Bells-and-Whistles](https://mlsanity.com/paper/2306.00989/) (2023)
- [Language as Queries for Referring Video Object Segmentation](https://mlsanity.com/paper/2201.00487/) (2022)
- [HTS-AT: A Hierarchical Token-Semantic Audio Transformer for Sound Classification and Detection](https://mlsanity.com/paper/2202.00874/) (2022)
- [Video Object Segmentation with Language Referring Expressions](https://mlsanity.com/paper/1803.08006/) (2018)
- [Audio-Visual Segmentation](https://mlsanity.com/paper/2207.05042/) (2022)
- [Actor and Action Video Segmentation from a Sentence](https://mlsanity.com/paper/1803.07485/) (2018)
- [Audio-Visual Segmentation with Semantics](https://mlsanity.com/paper/2301.13190/) (2023)
- [AVSegFormer: Audio-Visual Segmentation with Transformer](https://mlsanity.com/paper/2307.01146/) (2023)
- [AV-SAM: Segment Anything Model Meets Audio-Visual Localization and Segmentation](https://mlsanity.com/paper/2305.01836/) (2023)
- [CATR: Combinatorial-Dependence Audio-Queried Transformer for Audio-Visual Video Segmentation](https://mlsanity.com/paper/2309.09709/) (2023)
- [RoboGround: Robotic Manipulation with Grounded Vision-Language Priors](https://mlsanity.com/paper/2504.21530/) (2025)
- [Towards Robust Referring Video Object Segmentation with Cyclic Relational Consensus](https://mlsanity.com/paper/2207.01203/) (2022)
- [Annotation-free Audio-Visual Segmentation](https://mlsanity.com/paper/2305.11019/) (2023)
- [Omni-R1: Reinforcement Learning for Omnimodal Reasoning via Two-System Collaboration](https://mlsanity.com/paper/2505.20256/) (2025)
- [Prompting Segmentation with Sound Is Generalizable Audio-Visual Source Localizer](https://mlsanity.com/paper/2309.07929/) (2023)
- [Ref-AVS: Refer and Segment Objects in Audio-Visual Scenes](https://mlsanity.com/paper/2407.10957/) (2024)
- [Discovering Sounding Objects by Audio Queries for Audio Visual Segmentation](https://mlsanity.com/paper/2309.09501/) (2023)
- [EffiVED:Efficient Video Editing via Text-instruction Diffusion Models](https://mlsanity.com/paper/2403.11568/) (2024)
- [QDFormer: Towards Robust Audiovisual Segmentation in Complex Environments with Quantization-based Semantic Decomposition](https://mlsanity.com/paper/2310.00132/) (2023)
- [Crab: A Unified Audio-Visual Scene Understanding Model with Explicit Cooperation](https://mlsanity.com/paper/2503.13068/) (2025)
- [SAM2-LOVE: Segment Anything Model 2 in Language-aided Audio-Visual Scenes](https://mlsanity.com/paper/2506.01558/) (2025)
- [Towards Omnimodal Expressions and Reasoning in Referring Audio-Visual Segmentation](https://mlsanity.com/paper/2507.22886/) (2025)
- [Think Before You Segment: An Object-aware Reasoning Agent for Referring Audio-Visual Segmentation](https://mlsanity.com/paper/2508.04418/) (2025)
- [Transavs: End-To-End Audio-Visual Segmentation With Transformer](https://mlsanity.com/paper/2305.07223/) (2023)
- [AURORA:Augmented Understanding via Structured Reasoning and Reinforcement Learning for Reference Audio-Visual Segmentation](https://mlsanity.com/paper/2508.02149/) (2025)
- [Embodied Uncertainty-Aware Object Segmentation](https://mlsanity.com/paper/2408.04760/) (2024)

## Abstract (arXiv)

Referring Audio-Visual Segmentation (Ref-AVS) seeks to localize and segment target objects in video frames based on visual, auditory, and textual referring cues. The task is challenging because the relevance of different modalities varies across referring expressions and scenes, while existing methods typically treat multimodal cues as homogeneous inputs for fusion, prompting, or reasoning, making them vulnerable to irrelevant or misleading modalities. To address this problem, we propose PRIMED, inspired by the biased competition theory in cognitive neuroscience, which explicitly models both visual perception and language-driven prior modulation, and enables more accurate Ref-AVS by adaptive modality suppression. Specifically, a Modality Prior Decoder first estimates whether the referring expression relies primarily on audio, vision, or their joint interaction, generating a modality prior to adaptively guide high-level attention. A Token Distiller further extracts compact global visual tokens from high-level features and shares them across Competition-aware Cross-modal Fusion modules to provide hierarchical global context. Additionally, we introduce a Spatial-Aware Semantic Alignment loss to further enhance foreground-background discrimination through contrastive learning. Extensive experiments on the Ref-AVS benchmark demonstrate that PRIMED achieves state-of-the-art overall performance.