Prompting Segmentation with Sound Is Generalizable Audio-Visual Source Localizer

TL;DR

This paper introduces a novel encoder-prompt-decoder framework for audio-visual localization and segmentation, leveraging pre-trained models and semantic prompts to improve zero-shot and few-shot performance across unseen classes and datasets.

Contribution

It proposes the Semantic-aware Audio Prompt and Correlation Adapter to enhance generalization and reduce training efforts in audio-visual localization and segmentation tasks.

Findings

Outperforms fusion-based methods in unseen class scenarios

Effective in cross-dataset evaluations

Reduces training efforts with minimal fine-tuning

Abstract

Never having seen an object and heard its sound simultaneously, can the model still accurately localize its visual position from the input audio? In this work, we concentrate on the Audio-Visual Localization and Segmentation tasks but under the demanding zero-shot and few-shot scenarios. To achieve this goal, different from existing approaches that mostly employ the encoder-fusion-decoder paradigm to decode localization information from the fused audio-visual feature, we introduce the encoder-prompt-decoder paradigm, aiming to better fit the data scarcity and varying data distribution dilemmas with the help of abundant knowledge from pre-trained models. Specifically, we first propose to construct Semantic-aware Audio Prompt (SAP) to help the visual foundation model focus on sounding objects, meanwhile, the semantic gap between the visual and audio modalities is also encouraged to shrink. Then, we develop a Correlation Adapter (ColA) to keep minimal training efforts as well as maintain adequate knowledge of the visual foundation model. By equipping with these means, extensive experiments demonstrate that this new paradigm outperforms other fusion-based methods in both the unseen class and cross-dataset settings. We hope that our work can further promote the generalization study of Audio-Visual Localization and Segmentation in practical application scenarios.