Unraveling Instance Associations: A Closer Look for Audio-Visual Segmentation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911987692208128 |
|---|---|
| author | Chen, Yuanhong Liu, Yuyuan Wang, Hu Liu, Fengbei Wang, Chong Frazer, Helen Carneiro, Gustavo |
| author_facet | Chen, Yuanhong Liu, Yuyuan Wang, Hu Liu, Fengbei Wang, Chong Frazer, Helen Carneiro, Gustavo |
| contents | Audio-visual segmentation (AVS) is a challenging task that involves accurately segmenting sounding objects based on audio-visual cues. The effectiveness of audio-visual learning critically depends on achieving accurate cross-modal alignment between sound and visual objects. Successful audio-visual learning requires two essential components: 1) a challenging dataset with high-quality pixel-level multi-class annotated images associated with audio files, and 2) a model that can establish strong links between audio information and its corresponding visual object. However, these requirements are only partially addressed by current methods, with training sets containing biased audio-visual data, and models that generalise poorly beyond this biased training set. In this work, we propose a new cost-effective strategy to build challenging and relatively unbiased high-quality audio-visual segmentation benchmarks. We also propose a new informative sample mining method for audio-visual supervised contrastive learning to leverage discriminative contrastive samples to enforce cross-modal understanding. We show empirical results that demonstrate the effectiveness of our benchmark. Furthermore, experiments conducted on existing AVS datasets and on our new benchmark show that our method achieves state-of-the-art (SOTA) segmentation accuracy. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2304_02970 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Unraveling Instance Associations: A Closer Look for Audio-Visual Segmentation Chen, Yuanhong Liu, Yuyuan Wang, Hu Liu, Fengbei Wang, Chong Frazer, Helen Carneiro, Gustavo Computer Vision and Pattern Recognition Multimedia Audio-visual segmentation (AVS) is a challenging task that involves accurately segmenting sounding objects based on audio-visual cues. The effectiveness of audio-visual learning critically depends on achieving accurate cross-modal alignment between sound and visual objects. Successful audio-visual learning requires two essential components: 1) a challenging dataset with high-quality pixel-level multi-class annotated images associated with audio files, and 2) a model that can establish strong links between audio information and its corresponding visual object. However, these requirements are only partially addressed by current methods, with training sets containing biased audio-visual data, and models that generalise poorly beyond this biased training set. In this work, we propose a new cost-effective strategy to build challenging and relatively unbiased high-quality audio-visual segmentation benchmarks. We also propose a new informative sample mining method for audio-visual supervised contrastive learning to leverage discriminative contrastive samples to enforce cross-modal understanding. We show empirical results that demonstrate the effectiveness of our benchmark. Furthermore, experiments conducted on existing AVS datasets and on our new benchmark show that our method achieves state-of-the-art (SOTA) segmentation accuracy. |
| title | Unraveling Instance Associations: A Closer Look for Audio-Visual Segmentation |
| topic | Computer Vision and Pattern Recognition Multimedia |
| url | https://arxiv.org/abs/2304.02970 |