Stepping Stones: A Progressive Training Strategy for Audio-Visual Semantic Segmentation
- URL: http://arxiv.org/abs/2407.11820v3
- Date: Thu, 12 Sep 2024 09:20:26 GMT
- Title: Stepping Stones: A Progressive Training Strategy for Audio-Visual Semantic Segmentation
- Authors: Juncheng Ma, Peiwen Sun, Yaoting Wang, Di Hu,
- Abstract summary: Audio-Visual (AVS) aims to achieve pixel-level localization of sound sources in videos, while Audio-Visual Semantic (AVSS) pursues semantic understanding of audio-visual scenes.
Previous methods have struggled to handle this mashup of objectives in end-to-end training, resulting in insufficient learning and sub-optimization.
We propose a two-stage training strategy called textitStepping Stones, which decomposes the AVSS task into two simple subtasks from localization to semantic understanding, which are fully optimized in each stage to achieve step-by-step global optimization
- Score: 7.124066540020968
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Audio-Visual Segmentation (AVS) aims to achieve pixel-level localization of sound sources in videos, while Audio-Visual Semantic Segmentation (AVSS), as an extension of AVS, further pursues semantic understanding of audio-visual scenes. However, since the AVSS task requires the establishment of audio-visual correspondence and semantic understanding simultaneously, we observe that previous methods have struggled to handle this mashup of objectives in end-to-end training, resulting in insufficient learning and sub-optimization. Therefore, we propose a two-stage training strategy called \textit{Stepping Stones}, which decomposes the AVSS task into two simple subtasks from localization to semantic understanding, which are fully optimized in each stage to achieve step-by-step global optimization. This training strategy has also proved its generalization and effectiveness on existing methods. To further improve the performance of AVS tasks, we propose a novel framework Adaptive Audio Visual Segmentation, in which we incorporate an adaptive audio query generator and integrate masked attention into the transformer decoder, facilitating the adaptive fusion of visual and audio features. Extensive experiments demonstrate that our methods achieve state-of-the-art results on all three AVS benchmarks. The project homepage can be accessed at https://gewu-lab.github.io/stepping_stones/.
Related papers
- SpA2V: Harnessing Spatial Auditory Cues for Audio-driven Spatially-aware Video Generation [50.03810359300705]
SpA2V decomposes the generation process into two stages: audio-guided video planning and layout-grounded video generation.<n>We show that SpA2V excels in generating realistic videos with semantic and spatial alignment to the input audios.
arXiv Detail & Related papers (2025-08-01T17:05:04Z) - Bridging Audio and Vision: Zero-Shot Audiovisual Segmentation by Connecting Pretrained Models [13.63552417613795]
We propose a novel zero-shot AVS framework that eliminates task-specific training by leveraging multiple pretrained models.<n>Our approach integrates audio, vision, and text representations to bridge modality gaps, enabling precise sound source segmentation without AVS-specific annotations.
arXiv Detail & Related papers (2025-06-06T21:06:35Z) - CAV-MAE Sync: Improving Contrastive Audio-Visual Mask Autoencoders via Fine-Grained Alignment [76.32508013503653]
We propose CAV-MAE Sync as a simple yet effective extension of the original CAV-MAE framework for self-supervised audio-visual learning.<n>We tackle the mismatch between modalities by treating audio as a temporal sequence aligned with video frames, rather than using global representations.<n>We improve spatial localization by introducing learnable register tokens that reduce semantic load on patch tokens.
arXiv Detail & Related papers (2025-05-02T12:59:58Z) - Label-anticipated Event Disentanglement for Audio-Visual Video Parsing [61.08434062821899]
We introduce a new decoding paradigm, underlinelabel sunderlineemunderlineantic-based underlineprojection (LEAP)
LEAP works by iteratively projecting encoded latent features of audio/visual segments onto semantically independent label embeddings.
To facilitate the LEAP paradigm, we propose a semantic-aware optimization strategy, which includes a novel audio-visual semantic similarity loss function.
arXiv Detail & Related papers (2024-07-11T01:57:08Z) - CPM: Class-conditional Prompting Machine for Audio-visual Segmentation [17.477225065057993]
Class-conditional Prompting Machine (CPM) improves bipartite matching with a learning strategy combining class-agnostic queries with class-conditional queries.
We conduct experiments on AVS benchmarks, demonstrating that our method achieves state-of-the-art (SOTA) segmentation accuracy.
arXiv Detail & Related papers (2024-07-07T13:20:21Z) - 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) - Bootstrapping Audio-Visual Segmentation by Strengthening Audio Cues [75.73217916395386]
We propose a Bidirectional Audio-Visual Decoder (BAVD) with integrated bidirectional bridges.
This interaction narrows the modality imbalance, facilitating more effective learning of integrated audio-visual representations.
We also present a strategy for audio-visual frame-wise synchrony as fine-grained guidance of BAVD.
arXiv Detail & Related papers (2024-02-04T03:02:35Z) - Leveraging Foundation models for Unsupervised Audio-Visual Segmentation [49.94366155560371]
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.
arXiv Detail & Related papers (2023-09-13T05:05:47Z) - Improving Audio-Visual Speech Recognition by Lip-Subword Correlation
Based Visual Pre-training and Cross-Modal Fusion Encoder [58.523884148942166]
We propose two novel techniques to improve audio-visual speech recognition (AVSR) under a pre-training and fine-tuning training framework.
First, we explore the correlation between lip shapes and syllable-level subword units in Mandarin to establish good frame-level syllable boundaries from lip shapes.
Next, we propose an audio-guided cross-modal fusion encoder (CMFE) neural network to utilize main training parameters for multiple cross-modal attention layers.
arXiv Detail & Related papers (2023-08-14T08:19:24Z) - 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) - VATLM: Visual-Audio-Text Pre-Training with Unified Masked Prediction for
Speech Representation Learning [119.49605266839053]
We propose a unified cross-modal representation learning framework VATLM (Visual-Audio-Text Language Model)
The proposed VATLM employs a unified backbone network to model the modality-independent information.
In order to integrate these three modalities into one shared semantic space, VATLM is optimized with a masked prediction task of unified tokens.
arXiv Detail & Related papers (2022-11-21T09:10:10Z) - Audio-Visual Segmentation [47.10873917119006]
We propose to explore a new problem called audio-visual segmentation (AVS)
The goal is to output a pixel-level map of the object(s) that produce sound at the time of the image frame.
We construct the first audio-visual segmentation benchmark (AVSBench), providing pixel-wise annotations for the sounding objects in audible videos.
arXiv Detail & Related papers (2022-07-11T17:50:36Z)
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.