# Decoupled Audio-Visual Dataset Distillation

arXiv: https://arxiv.org/abs/2511.17890 · HTML: https://mlsanity.com/paper/2511.17890/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 39 of its 57 references that are in the map.
- First posted on arXiv 22 Nov 2025.

## Builds on (most cited first, 30 of 39)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [ImageBind: One Embedding Space To Bind Them All](https://mlsanity.com/paper/2305.05665/) (2023)
- [VGGSound: A Large-scale Audio-Visual Dataset](https://mlsanity.com/paper/2004.14368/) (2020)
- [Dataset Condensation with Gradient Matching](https://mlsanity.com/paper/2006.05929/) (2020)
- [Dataset Distillation by Matching Training Trajectories](https://mlsanity.com/paper/2203.11932/) (2022)
- [Dataset Condensation with Distribution Matching](https://mlsanity.com/paper/2110.04181/) (2021)
- [Dataset Condensation with Differentiable Siamese Augmentation](https://mlsanity.com/paper/2102.08259/) (2021)
- [Dataset Condensation via Efficient Synthetic-Data Parameterization](https://mlsanity.com/paper/2205.14959/) (2022)
- [Multi-modal Learning with Missing Modality via Shared-Specific Feature Modelling](https://mlsanity.com/paper/2307.14126/) (2023)
- [Efficient Deep Learning: A Survey on Making Deep Learning Models Smaller, Faster, and Better](https://mlsanity.com/paper/2106.08962/) (2021)
- [Audio-Visual Segmentation](https://mlsanity.com/paper/2207.05042/) (2022)
- [The Sound of Motions](https://mlsanity.com/paper/1904.05979/) (2019)
- [Contrastive Audio-Visual Masked Autoencoder](https://mlsanity.com/paper/2210.07839/) (2022)
- [Minimizing the Accumulated Trajectory Error to Improve Dataset Distillation](https://mlsanity.com/paper/2211.11004/) (2022)
- [Improved Distribution Matching for Dataset Condensation](https://mlsanity.com/paper/2307.09742/) (2023)
- [Privacy for Free: How does Dataset Condensation Help Privacy?](https://mlsanity.com/paper/2206.00240/) (2022)
- [Generative Teaching Networks: Accelerating Neural Architecture Search by Learning to Generate Synthetic Training Data](https://mlsanity.com/paper/1912.07768/) (2019)
- [Efficient Dataset Distillation via Minimax Diffusion](https://mlsanity.com/paper/2311.15529/) (2023)
- [Audio-Visual Grouping Network for Sound Localization from Mixtures](https://mlsanity.com/paper/2303.17056/) (2023)
- [Soft-Label Anonymous Gastric X-ray Image Distillation](https://mlsanity.com/paper/2104.02857/) (2021)
- [Audiovisual Masked Autoencoders](https://mlsanity.com/paper/2212.05922/) (2022)
- [Multimodal Remote Sensing Benchmark Datasets for Land Cover Classification with A Shared and Specific Feature Learning Model](https://mlsanity.com/paper/2105.10196/) (2021)
- [Compressed Gastric Image Generation Based on Soft-Label Dataset Distillation for Medical Data Sharing](https://mlsanity.com/paper/2209.14635/) (2022)
- [Exploiting Inter-sample and Inter-feature Relations in Dataset Distillation](https://mlsanity.com/paper/2404.00563/) (2024)
- [iQuery: Instruments as Queries for Audio-Visual Sound Separation](https://mlsanity.com/paper/2212.03814/) (2022)
- [Dataset Distillation Using Parameter Pruning](https://mlsanity.com/paper/2209.14609/) (2022)
- [Towards Open-Vocabulary Audio-Visual Event Localization](https://mlsanity.com/paper/2411.11278/) (2024)
- [Dataset Distillation for Medical Dataset Sharing](https://mlsanity.com/paper/2209.14603/) (2022)
- [Summarizing Stream Data for Memory-Constrained Online Continual Learning](https://mlsanity.com/paper/2305.16645/) (2023)
- [Importance-Aware Adaptive Dataset Distillation](https://mlsanity.com/paper/2401.15863/) (2024)

## Built on by (most cited first, 7 of 7)

- [FD2: A Dedicated Framework for Fine-Grained Dataset Distillation](https://mlsanity.com/paper/2603.25144/) (2026)
- [Foreground-Aware Dataset Distillation via Dynamic Patch Selection](https://mlsanity.com/paper/2601.02727/) (2026)
- [Difficulty-guided Sampling: Bridging the Target Gap between Dataset Distillation and Downstream Tasks](https://mlsanity.com/paper/2601.10090/) (2026)
- [Omnimodal Dataset Distillation via High-order Proxy Alignment](https://mlsanity.com/paper/2604.10666/) (2026)
- [Self-Supervised Representation-Guided Generative Dataset Distillation](https://mlsanity.com/paper/2608.03218/) (2026)
- [DeCO: Discriminative Evidence Composition for Fine-Grained Dataset Distillation](https://mlsanity.com/paper/2608.25480/) (2026)
- [PSM: Dataset Distillation Based on Precise Statistical Matching by Difficulty](https://mlsanity.com/paper/2609.34299/) (2026)

## Abstract (arXiv)

Audio-Visual Dataset Distillation aims to compress large-scale datasets into compact subsets while preserving the performance of the original data. However, conventional Distribution Matching (DM) methods struggle to capture intrinsic cross-modal alignment. Subsequent studies have attempted to introduce cross-modal matching, but two major challenges remain: (i) independently and randomly initialized encoders lead to inconsistent modality mapping spaces, increasing training difficulty; and (ii) direct interactions between modalities tend to damage modality-specific (private) information, thereby degrading the quality of the distilled data. To address these challenges, we propose DAVDD, a pretraining-based decoupled audio-visual distillation framework. DAVDD leverages a diverse pretrained bank to obtain stable modality features and uses a lightweight decoupler bank to disentangle them into common and private representations. To effectively preserve cross-modal structure, we further introduce Common Intermodal Matching together with a Sample-Distribution Joint Alignment strategy, ensuring that shared representations are aligned both at the sample level and the global distribution level. Meanwhile, private representations are entirely isolated from cross-modal interaction, safeguarding modality-specific cues throughout distillation. Extensive experiments across multiple benchmarks show that DAVDD achieves state-of-the-art results under all IPC settings, demonstrating the effectiveness of decoupled representation learning for high-quality audio-visual dataset distillation. Code will be released.