Audio-Enhanced Vision-Language Modeling with Latent Space Broadening for High Quality Data Expansion

• URL: http://arxiv.org/abs/2503.17551v1
• Date: Fri, 21 Mar 2025 21:55:05 GMT
• Title: Audio-Enhanced Vision-Language Modeling with Latent Space Broadening for High Quality Data Expansion
• Authors: Yu Sun, Yin Li, Ruixiao Sun, Chunhui Liu, Fangming Zhou, Ze Jin, Linjie Wang, Xiang Shen, Zhuolin Hao, Hongyu Xiong,
• Abstract summary: Transformer-based multimodal models are widely used in industrial-scale recommendation, search, and advertising systems.<n>We propose kNN-based Latent Space Broadening (LSB) to enhance AL efficiency and Vision-Language Modeling with Audio Enhancement (VLMAE)<n>This system deployed in production systems, leading to significant business gains.
• Score: 12.212623921747264
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Transformer-based multimodal models are widely used in industrial-scale recommendation, search, and advertising systems for content understanding and relevance ranking. Enhancing labeled training data quality and cross-modal fusion significantly improves model performance, influencing key metrics such as quality view rates and ad revenue. High-quality annotations are crucial for advancing content modeling, yet traditional statistical-based active learning (AL) methods face limitations: they struggle to detect overconfident misclassifications and are less effective in distinguishing semantically similar items in deep neural networks. Additionally, audio information plays an increasing role, especially in short-video platforms, yet most pre-trained multimodal architectures primarily focus on text and images. While training from scratch across all three modalities is possible, it sacrifices the benefits of leveraging existing pre-trained visual-language (VL) and audio models. To address these challenges, we propose kNN-based Latent Space Broadening (LSB) to enhance AL efficiency and Vision-Language Modeling with Audio Enhancement (VLMAE), a mid-fusion approach integrating audio into VL models. This system deployed in production systems, leading to significant business gains.

Related papers

• FSSUAVL: A Discriminative Framework using Vision Models for Federated Self-Supervised Audio and Image Understanding [10.897206681590541]
  We introduce textttFSSUAVL, a single deep model pretrained in Federated Learning. Instead of aligning the audio and image modalities, textttFSSUAVL jointly discriminates them by projecting them into a common embedding space. Our experiments with CNN and ViT demonstrate that textttFSSUAVL significantly improves performance across various image- and audio-based downstream tasks.
  arXiv  Detail & Related papers  (2025-04-13T11:04:43Z)
• Bridging The Multi-Modality Gaps of Audio, Visual and Linguistic for Speech Enhancement [36.136070412464214]
  Speech Enhancement (SE) aims to improve the quality of noisy speech.<n>We propose a novel multi-modality learning framework for SE.<n>We show that our proposed AVSE system significantly enhances speech quality and reduces generative artifacts.
  arXiv  Detail & Related papers  (2025-01-23T04:36:29Z)
• ADEM-VL: Adaptive and Embedded Fusion for Efficient Vision-Language Tuning [38.26304604660713]
  ADEM-VL is an efficient vision-language method that tunes models based on pretrained large language models. Our framework surpasses existing methods by an average accuracy of 0.77% on ScienceQA dataset.
  arXiv  Detail & Related papers  (2024-10-23T11:31:06Z)
• RA-BLIP: Multimodal Adaptive Retrieval-Augmented Bootstrapping Language-Image Pre-training [55.54020926284334]
  Multimodal Large Language Models (MLLMs) have recently received substantial interest, which shows their emerging potential as general-purpose models for various vision-language tasks. Retrieval augmentation techniques have proven to be effective plugins for both LLMs and MLLMs. In this study, we propose multimodal adaptive Retrieval-Augmented Bootstrapping Language-Image Pre-training (RA-BLIP), a novel retrieval-augmented framework for various MLLMs.
  arXiv  Detail & Related papers  (2024-10-18T03:45:19Z)
• Prompting Video-Language Foundation Models with Domain-specific Fine-grained Heuristics for Video Question Answering [71.62961521518731]
  HeurVidQA is a framework that leverages domain-specific entity-actions to refine pre-trained video-language foundation models. Our approach treats these models as implicit knowledge engines, employing domain-specific entity-action prompters to direct the model's focus toward precise cues that enhance reasoning.
  arXiv  Detail & Related papers  (2024-10-12T06:22:23Z)
• NVLM: Open Frontier-Class Multimodal LLMs [64.00053046838225]
  We introduce NVLM 1.0, a family of frontier-class multimodal large language models (LLMs) that achieve state-of-the-art results on vision-language tasks. We propose a novel architecture that enhances both training efficiency and multimodal reasoning capabilities. We develop production-grade multimodality for the NVLM-1.0 models, enabling them to excel in vision-language tasks.
  arXiv  Detail & Related papers  (2024-09-17T17:59:06Z)
• Chain-of-Spot: Interactive Reasoning Improves Large Vision-Language Models [81.71651422951074]
  Chain-of-Spot (CoS) method is a novel approach that enhances feature extraction by focusing on key regions of interest. This technique allows LVLMs to access more detailed visual information without altering the original image resolution. Our empirical findings demonstrate a significant improvement in LVLMs' ability to understand and reason about visual content.
  arXiv  Detail & Related papers  (2024-03-19T17:59:52Z)
• Tuning Large Multimodal Models for Videos using Reinforcement Learning from AI Feedback [38.708690624594794]
  Video and text multimodal alignment remains challenging, primarily due to the deficient volume and quality of multimodal instruction-tune data. We present a novel alignment strategy that employs multimodal AI system to oversee itself called Reinforcement Learning from AI Feedback (RLAIF) In specific, we propose context-aware reward modeling by providing detailed video descriptions as context during the generation of preference feedback.
  arXiv  Detail & Related papers  (2024-02-06T06:27:40Z)
• 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)
• UniDiff: Advancing Vision-Language Models with Generative and Discriminative Learning [86.91893533388628]
  This paper presents UniDiff, a unified multi-modal model that integrates image-text contrastive learning (ITC), text-conditioned image synthesis learning (IS), and reciprocal semantic consistency modeling (RSC) UniDiff demonstrates versatility in both multi-modal understanding and generative tasks.
  arXiv  Detail & Related papers  (2023-06-01T15:39:38Z)
• Leveraging Uni-Modal Self-Supervised Learning for Multimodal Audio-Visual Speech Recognition [23.239078852797817]
  We leverage uni-modal self-supervised learning to promote the multimodal audio-visual speech recognition (AVSR) In particular, we first train audio and visual encoders on a large-scale uni-modal dataset, then we integrate components of both encoders into a larger multimodal framework. Our model is experimentally validated on both word-level and sentence-level AVSR tasks.
  arXiv  Detail & Related papers  (2022-02-24T15:12:17Z)

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.