Siamese Vision Transformers are Scalable Audio-visual Learners

• URL: http://arxiv.org/abs/2403.19638v1
• Date: Thu, 28 Mar 2024 17:52:24 GMT
• Title: Siamese Vision Transformers are Scalable Audio-visual Learners
• Authors: Yan-Bo Lin, Gedas Bertasius,
• Abstract summary: We investigate using an audio-visual siamese network (AVSiam) for efficient and scalable audio-visual pretraining. Our framework uses a single shared vision transformer backbone to process audio and visual inputs. Our method can robustly handle audio, visual, and audio-visual inputs with a single shared ViT backbone.
• Score: 19.916919837694802
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Traditional audio-visual methods rely on independent audio and visual backbones, which is costly and not scalable. In this work, we investigate using an audio-visual siamese network (AVSiam) for efficient and scalable audio-visual pretraining. Our framework uses a single shared vision transformer backbone to process audio and visual inputs, improving its parameter efficiency, reducing the GPU memory footprint, and allowing us to scale our method to larger datasets and model sizes. We pretrain our model using a contrastive audio-visual matching objective with a multi-ratio random masking scheme, which enables our model to process larger audio-visual instance batches, helpful for contrastive learning. Unlike prior audio-visual methods, our method can robustly handle audio, visual, and audio-visual inputs with a single shared ViT backbone. Furthermore, despite using the shared backbone for both modalities, AVSiam achieves competitive or even better results than prior methods on AudioSet and VGGSound for audio-visual classification and retrieval. Our code is available at https://github.com/GenjiB/AVSiam

Related papers

• From Vision to Audio and Beyond: A Unified Model for Audio-Visual Representation and Generation [17.95017332858846]
  We introduce a novel framework called Vision to Audio and Beyond (VAB) to bridge the gap between audio-visual representation learning and vision-to-audio generation. VAB uses a pre-trained audio tokenizer and an image encoder to obtain audio tokens and visual features, respectively. Our experiments showcase the efficiency of VAB in producing high-quality audio from video, and its capability to acquire semantic audio-visual features.
  arXiv  Detail & Related papers  (2024-09-27T20:26:34Z)
• Seeing and Hearing: Open-domain Visual-Audio Generation with Diffusion Latent Aligners [69.70590867769408]
  Video and audio content creation serves as the core technique for the movie industry and professional users. Existing diffusion-based methods tackle video and audio generation separately, which hinders the technique transfer from academia to industry. In this work, we aim at filling the gap, with a carefully designed optimization-based framework for cross-visual-audio and joint-visual-audio generation.
  arXiv  Detail & Related papers  (2024-02-27T17:57:04Z)
• 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)
• AudioFormer: Audio Transformer learns audio feature representations from discrete acoustic codes [6.375996974877916]
  We propose a method named AudioFormer, which learns audio feature representations through the acquisition of discrete acoustic codes. Our research outcomes demonstrate that AudioFormer attains significantly improved performance compared to prevailing monomodal audio classification models.
  arXiv  Detail & Related papers  (2023-08-14T15:47:25Z)
• Visually-Guided Sound Source Separation with Audio-Visual Predictive Coding [57.08832099075793]
  Visually-guided sound source separation consists of three parts: visual feature extraction, multimodal feature fusion, and sound signal processing. This paper presents audio-visual predictive coding (AVPC) to tackle this task in parameter harmonizing and more effective manner. In addition, we develop a valid self-supervised learning strategy for AVPC via co-predicting two audio-visual representations of the same sound source.
  arXiv  Detail & Related papers  (2023-06-19T03:10:57Z)
• Sound to Visual Scene Generation by Audio-to-Visual Latent Alignment [22.912401512161132]
  We design a model that works by scheduling the learning procedure of each model component to associate audio-visual modalities. We translate the input audio to visual features, then use a pre-trained generator to produce an image. We obtain substantially better results on the VEGAS and VGGSound datasets than prior approaches.
  arXiv  Detail & Related papers  (2023-03-30T16:01:50Z)
• Vision Transformers are Parameter-Efficient Audio-Visual Learners [95.59258503297195]
  We propose a latent audio-visual hybrid (LAVISH) adapter that adapts pretrained ViTs to audio-visual tasks. Our approach achieves competitive or even better performance on various audio-visual tasks.
  arXiv  Detail & Related papers  (2022-12-15T17:31:54Z)
• Contrastive Audio-Visual Masked Autoencoder [85.53776628515561]
  Contrastive Audio-Visual Masked Auto-Encoder (CAV-MAE) Our fully self-supervised pretrained CAV-MAE achieves a new SOTA accuracy of 65.9% on VGGSound.
  arXiv  Detail & Related papers  (2022-10-02T07:29:57Z)
• Estimating Visual Information From Audio Through Manifold Learning [14.113590443352495]
  We propose a new framework for extracting visual information about a scene only using audio signals. Our framework is based on Manifold Learning and consists of two steps. We show that our method is able to produce meaningful images from audio using a publicly available audio/visual dataset.
  arXiv  Detail & Related papers  (2022-08-03T20:47:11Z)
• VGGSound: A Large-scale Audio-Visual Dataset [160.1604237188594]
  We propose a scalable pipeline to create an audio dataset from open-source media. We use this pipeline to curate the VGGSound dataset consisting of more than 210k videos for 310 audio classes. The resulting dataset can be used for training and evaluating audio recognition models.
  arXiv  Detail & Related papers  (2020-04-29T17:46:54Z)

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.