# uaMix-MAE: Efficient Tuning of Pretrained Audio Transformers with Unsupervised Audio Mixtures

arXiv: https://arxiv.org/abs/2403.09579 · HTML: https://mlsanity.com/paper/2403.09579/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 33 of its 37 references that are in the map.
- First posted on arXiv 14 Mar 2024.

## Builds on (most cited first, 30 of 33)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [Zero-Shot Text-to-Image Generation](https://mlsanity.com/paper/2102.12092/) (2021)
- [CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features](https://mlsanity.com/paper/1905.04899/) (2019)
- [BEiT: BERT Pre-Training of Image Transformers](https://mlsanity.com/paper/2106.08254/) (2021)
- [Speech Commands: A Dataset for Limited-Vocabulary Speech Recognition](https://mlsanity.com/paper/1804.03209/) (2018)
- [VoxCeleb: a large-scale speaker identification dataset](https://mlsanity.com/paper/1706.08612/) (2017)
- [AST: Audio Spectrogram Transformer](https://mlsanity.com/paper/2104.01778/) (2021)
- [BEATs: Audio Pre-Training with Acoustic Tokenizers](https://mlsanity.com/paper/2212.09058/) (2022)
- [With a Little Help from My Friends: Nearest-Neighbor Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2104.14548/) (2021)
- [Masked Autoencoders that Listen](https://mlsanity.com/paper/2207.06405/) (2022)
- [Neural Audio Synthesis of Musical Notes with WaveNet Autoencoders](https://mlsanity.com/paper/1704.01279/) (2017)
- [How Well Do Self-Supervised Models Transfer?](https://mlsanity.com/paper/2011.13377/) (2020)
- [Wav2CLIP: Learning Robust Audio Representations From CLIP](https://mlsanity.com/paper/2110.11499/) (2021)
- [Contrastive Learning of General-Purpose Audio Representations](https://mlsanity.com/paper/2010.10915/) (2020)
- [BYOL for Audio: Self-Supervised Learning for General-Purpose Audio Representation](https://mlsanity.com/paper/2103.06695/) (2021)
- [MAE-AST: Masked Autoencoding Audio Spectrogram Transformer](https://mlsanity.com/paper/2203.16691/) (2022)
- [Un-Mix: Rethinking Image Mixtures for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/2003.05438/) (2020)
- [Masked Spectrogram Modeling using Masked Autoencoders for Learning General-purpose Audio Representation](https://mlsanity.com/paper/2204.12260/) (2022)
- [Masked Spectrogram Prediction For Self-Supervised Audio Pre-Training](https://mlsanity.com/paper/2204.12768/) (2022)
- [General-purpose Tagging of Freesound Audio with AudioSet Labels: Task Description, Dataset, and Baseline](https://mlsanity.com/paper/1807.09902/) (2018)
- [Training Vision Transformers with Only 2040 Images](https://mlsanity.com/paper/2201.10728/) (2022)
- [Masked Modeling Duo: Learning Representations by Encouraging Both Networks to Model the Input](https://mlsanity.com/paper/2210.14648/) (2022)

## Abstract (arXiv)

Masked Autoencoders (MAEs) learn rich low-level representations from unlabeled data but require substantial labeled data to effectively adapt to downstream tasks. Conversely, Instance Discrimination (ID) emphasizes high-level semantics, offering a potential solution to alleviate annotation requirements in MAEs. Although combining these two approaches can address downstream tasks with limited labeled data, naively integrating ID into MAEs leads to extended training times and high computational costs. To address this challenge, we introduce uaMix-MAE, an efficient ID tuning strategy that leverages unsupervised audio mixtures. Utilizing contrastive tuning, uaMix-MAE aligns the representations of pretrained MAEs, thereby facilitating effective adaptation to task-specific semantics. To optimize the model with small amounts of unlabeled data, we propose an audio mixing technique that manipulates audio samples in both input and virtual label spaces. Experiments in low/few-shot settings demonstrate that modelname achieves 4-6% accuracy improvements over various benchmarks when tuned with limited unlabeled data, such as AudioSet-20K. Code is available at https://github.com/PLAN-Lab/uamix-MAE