SOUPLE: Enhancing Audio-Visual Localization and Segmentation with Learnable Prompt Contexts
This work addresses audio-visual localization and segmentation for multimodal AI applications, representing an incremental improvement over existing methods.
The paper tackled the challenge of applying CLIP models to audio-visual localization by proposing SOUPLE, which uses learnable context tokens to bridge audio and visual semantics, resulting in improved performance on datasets like VGGSound and AVSBench.
Large-scale pre-trained image-text models exhibit robust multimodal representations, yet applying the Contrastive Language-Image Pre-training (CLIP) model to audio-visual localization remains challenging. Replacing the classification token ([CLS]) with an audio-embedded token ([V_A]) struggles to capture semantic cues, and the prompt "a photo of a [V_A]" fails to establish meaningful connections between audio embeddings and context tokens. To address these issues, we propose Sound-aware Prompt Learning (SOUPLE), which replaces fixed prompts with learnable context tokens. These tokens incorporate visual features to generate conditional context for a mask decoder, effectively bridging semantic correspondence between audio and visual inputs. Experiments on VGGSound, SoundNet, and AVSBench demonstrate that SOUPLE improves localization and segmentation performance.