Leveraging Foundation models for Unsupervised Audio-Visual Segmentation
- URL: http://arxiv.org/abs/2309.06728v1
- Date: Wed, 13 Sep 2023 05:05:47 GMT
- Title: Leveraging Foundation models for Unsupervised Audio-Visual Segmentation
- Authors: Swapnil Bhosale, Haosen Yang, Diptesh Kanojia, Xiatian Zhu
- Abstract summary: Audio-Visual (AVS) aims to precisely outline audible objects in a visual scene at the pixel level.
Existing AVS methods require fine-grained annotations of audio-mask pairs in supervised learning fashion.
We introduce unsupervised audio-visual segmentation with no need for task-specific data annotations and model training.
- Score: 49.94366155560371
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Audio-Visual Segmentation (AVS) aims to precisely outline audible objects in
a visual scene at the pixel level. Existing AVS methods require fine-grained
annotations of audio-mask pairs in supervised learning fashion. This limits
their scalability since it is time consuming and tedious to acquire such
cross-modality pixel level labels. To overcome this obstacle, in this work we
introduce unsupervised audio-visual segmentation with no need for task-specific
data annotations and model training. For tackling this newly proposed problem,
we formulate a novel Cross-Modality Semantic Filtering (CMSF) approach to
accurately associate the underlying audio-mask pairs by leveraging the
off-the-shelf multi-modal foundation models (e.g., detection [1], open-world
segmentation [2] and multi-modal alignment [3]). Guiding the proposal
generation by either audio or visual cues, we design two training-free
variants: AT-GDINO-SAM and OWOD-BIND. Extensive experiments on the AVS-Bench
dataset show that our unsupervised approach can perform well in comparison to
prior art supervised counterparts across complex scenarios with multiple
auditory objects. Particularly, in situations where existing supervised AVS
methods struggle with overlapping foreground objects, our models still excel in
accurately segmenting overlapped auditory objects. Our code will be publicly
released.
Related papers
- Towards Open-Vocabulary Audio-Visual Event Localization [59.23161248808759]
We introduce the Open-Vocabulary Audio-Visual Event localization problem.
This problem requires localizing audio-visual events and predicting explicit categories for both seen and unseen data at inference.
We propose the OV-AVEBench dataset, comprising 24,800 videos across 67 real-life audio-visual scenes.
arXiv Detail & Related papers (2024-11-18T04:35:20Z) - Unsupervised Audio-Visual Segmentation with Modality Alignment [42.613786372067814]
Audio-Visual aims to identify, at the pixel level, the object in a visual scene that produces a given sound.
Current AVS methods rely on costly fine-grained annotations of mask-audio pairs, making them impractical for scalability.
We propose an unsupervised learning method, named Modality Correspondence Alignment (MoCA), which seamlessly integrates off-the-shelf foundation models.
arXiv Detail & Related papers (2024-03-21T07:56:09Z) - Weakly-Supervised Audio-Visual Segmentation [44.632423828359315]
We present a novel Weakly-Supervised Audio-Visual framework, namely WS-AVS, that can learn multi-scale audio-visual alignment with multi-instance contrastive learning for audio-visual segmentation.
Experiments on AVSBench demonstrate the effectiveness of our WS-AVS in the weakly-supervised audio-visual segmentation of single-source and multi-source scenarios.
arXiv Detail & Related papers (2023-11-25T17:18:35Z) - Improving Audio-Visual Segmentation with Bidirectional Generation [40.78395709407226]
We introduce a bidirectional generation framework for audio-visual segmentation.
This framework establishes robust correlations between an object's visual characteristics and its associated sound.
We also introduce an implicit volumetric motion estimation module to handle temporal dynamics.
arXiv Detail & Related papers (2023-08-16T11:20:23Z) - Annotation-free Audio-Visual Segmentation [46.42570058385209]
We propose a novel pipeline for generating artificial data for the Audio-Visual task without extra manual annotations.
We leverage existing image segmentation and audio datasets and match the image-mask pairs with its corresponding audio samples using category labels.
We also introduce a lightweight model SAMA-AVS which adapts the pre-trained segment anything model(SAM) to the AVS task.
arXiv Detail & Related papers (2023-05-18T14:52:45Z) - Multi-Granularity Denoising and Bidirectional Alignment for Weakly
Supervised Semantic Segmentation [75.32213865436442]
We propose an end-to-end multi-granularity denoising and bidirectional alignment (MDBA) model to alleviate the noisy label and multi-class generalization issues.
The MDBA model can reach the mIoU of 69.5% and 70.2% on validation and test sets for the PASCAL VOC 2012 dataset.
arXiv Detail & Related papers (2023-05-09T03:33:43Z) - Unraveling Instance Associations: A Closer Look for Audio-Visual Segmentation [18.001730255429347]
Audio-visual segmentation (AVS) is a challenging task that involves accurately segmenting sounding objects based on audio-visual cues.
We propose a new cost-effective strategy to build challenging and relatively unbiased high-quality audio-visual segmentation benchmarks.
Experiments conducted on existing AVS datasets and on our new benchmark show that our method achieves state-of-the-art (SOTA) segmentation accuracy.
arXiv Detail & Related papers (2023-04-06T09:54:06Z) - A Simple Framework for Open-Vocabulary Segmentation and Detection [85.21641508535679]
We present OpenSeeD, a simple Open-vocabulary and Detection framework that jointly learns from different segmentation and detection datasets.
We first introduce a pre-trained text encoder to encode all the visual concepts in two tasks and learn a common semantic space for them.
After pre-training, our model exhibits competitive or stronger zero-shot transferability for both segmentation and detection.
arXiv Detail & Related papers (2023-03-14T17:58:34Z) - DETA: Denoised Task Adaptation for Few-Shot Learning [135.96805271128645]
Test-time task adaptation in few-shot learning aims to adapt a pre-trained task-agnostic model for capturing taskspecific knowledge.
With only a handful of samples available, the adverse effect of either the image noise (a.k.a. X-noise) or the label noise (a.k.a. Y-noise) from support samples can be severely amplified.
We propose DEnoised Task Adaptation (DETA), a first, unified image- and label-denoising framework to existing task adaptation approaches.
arXiv Detail & Related papers (2023-03-11T05:23:20Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.