paper-with-me

Papers

Vision Transformers are Parameter-Efficient Audio-Visual Learners

2022-12-15 · CVPR 2023 1 · Yan-Bo Lin, Yi-Lin Sung, Jie Lei, Mohit Bansal, Gedas Bertasius

Vision transformers (ViTs) have achieved impressive results on various computer vision tasks in the last several years. In this work, we study the capability of frozen ViTs, pretrained only on visual data, to generalize to audio-visual data without finetuning any of its original parameters. To do so, we propose a latent audio-visual hybrid (LAVISH) adapter that adapts pretrained ViTs to audio-visual tasks by injecting a small number of trainable parameters into every layer of a frozen ViT. To efficiently fuse visual and audio cues, our LAVISH adapter uses a small set of latent tokens, which form an attention bottleneck, thus, eliminating the quadratic cost of standard cross-attention. Compared to the existing modality-specific audio-visual methods, our approach achieves competitive or even better performance on various audio-visual tasks while using fewer tunable parameters and without relying on costly audio pretraining or external audio encoders. Our code is available at https://genjib.github.io/project_page/LAVISH/

📄 PDF Abstract BibTeX arXiv:2212.07983

Code (1)

GenjiB/LAVISH 공식 구현 pytorch

Tasks

Audio-visual Question AnsweringAUDIO-VISUAL QUESTION ANSWERING (MUSIC-AVQA-v2.0)

Methods 이 논문이 사용한 방법론

Adapter 설명 없음

Similar Papers 제목 키워드 기반

Siamese Vision Transformers are Scalable Audio-visual Learners

2024-03-28 · Yan-Bo Lin, Gedas Bertasius

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 au…

Contrastive LearningGPURetrieval

MAViL: Masked Audio-Video Learners

2022-12-15 · NeurIPS 2023 11 · Po-Yao Huang, Vasu Sharma, Hu Xu, Chaitanya Ryali 외

We present Masked Audio-Video Learners (MAViL) to train audio-visual representations. Our approach learns with three complementary forms of self-supervision: (1) reconstruction of masked audio and video input data, (2) i…

Contrastive LearningRetrieval

MA-AVT: Modality Alignment for Parameter-Efficient Audio-Visual Transformers

2024-06-07 · Tanvir Mahmud, Shentong Mo, Yapeng Tian, Diana Marculescu

Recent advances in pre-trained vision transformers have shown promise in parameter-efficient audio-visual learning without audio pre-training. However, few studies have investigated effective methods for aligning multimo…

audio-visual learningContrastive Learning

Parameter Efficient Multimodal Transformers for Video Representation Learning

2020-12-08 · ICLR 2021 1 · Sangho Lee, Youngjae Yu, Gunhee Kim, Thomas Breuel 외

The recent success of Transformers in the language domain has motivated adapting it to a multimodal setting, where a new visual model is trained in tandem with an already pretrained language model. However, due to the ex…

Language ModelingLanguage ModellingRepresentation Learning

Revisiting Audio-Visual Segmentation with Vision-Centric Transformer

2025-01-01 · CVPR 2025 1 · Shaofei Huang, Rui Ling, Tianrui Hui, Hongyu Li 외

Audio-Visual Segmentation (AVS) aims to segment sound-producing objects in video frames based on the associated audio signal. Prevailing AVS methods typically adopt an audio-centric Transformer architecture, where ob…