BROWSE
Detail
Conference Paper
MarginNCE: Robust Sound Localization with a Negative Margin
Cited 10 time in 
Share 
Share
- Authors
- Sooyoung Park, Arda Senocak, Joon Son Chung
- Issue Date
- 2023-06
- Citation
- International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2023, pp.1-5
- Publisher
- IEEE
- Language
- English
- Type
- Conference Paper
- Abstract
- The goal of this work is to localize sound sources in visual scenes with a self-supervised approach. Contrastive learning in the context of sound source localization leverages the natural correspondence between audio and visual signals where the audio-visual pairs from the same source are assumed as positive, while randomly selected pairs are negatives. However, this approach brings in noisy correspondences; for example, positive audio and visual pair signals that may be unrelated to each other, or negative pairs that may contain semantically similar samples to the positive one. Our key contribution in this work is to show that using a less strict decision boundary in contrastive learning can alleviate the effect of noisy correspondences in sound source localization. We propose a simple yet effective approach by slightly modifying the contrastive loss with a negative margin. Extensive experimental results show that our approach gives on-par or better performance than the state-of-the-art methods. Furthermore, we demonstrate that the introduction of a negative margin to existing methods results in a consistent improvement in performance.
- KSP Keywords
- Audio-visual, Similar samples, Sound localization, Visual scenes, Visual signals, decision boundary, sound source localization, state-of-The-Art, supervised approach