# When Vision Models Meet Parameter Efficient Look-Aside Adapters Without Large-Scale Audio Pretraining

arXiv: https://arxiv.org/abs/2412.05951 · HTML: https://mlsanity.com/paper/2412.05951/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 25 references that are in the map.
- First posted on arXiv 8 Dec 2024.

## Builds on (most cited first, 21 of 21)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [Prefix-Tuning: Optimizing Continuous Prompts for Generation](https://mlsanity.com/paper/2101.00190/) (2021)
- [The Power of Scale for Parameter-Efficient Prompt Tuning](https://mlsanity.com/paper/2104.08691/) (2021)
- [Exploring Simple Siamese Representation Learning](https://mlsanity.com/paper/2011.10566/) (2020)
- [Towards a Unified View of Parameter-Efficient Transfer Learning](https://mlsanity.com/paper/2110.04366/) (2021)
- [Speech Commands: A Dataset for Limited-Vocabulary Speech Recognition](https://mlsanity.com/paper/1804.03209/) (2018)
- [AST: Audio Spectrogram Transformer](https://mlsanity.com/paper/2104.01778/) (2021)
- [PANNs: Large-Scale Pretrained Audio Neural Networks for Audio Pattern Recognition](https://mlsanity.com/paper/1912.10211/) (2019)
- [Learning multiple visual domains with residual adapters](https://mlsanity.com/paper/1705.08045/) (2017)
- [Masked Autoencoders that Listen](https://mlsanity.com/paper/2207.06405/) (2022)
- [SSAST: Self-Supervised Audio Spectrogram Transformer](https://mlsanity.com/paper/2110.09784/) (2021)
- [Contrastive Audio-Visual Masked Autoencoder](https://mlsanity.com/paper/2210.07839/) (2022)
- [Convolutional Bypasses Are Better Vision Transformer Adapters](https://mlsanity.com/paper/2207.07039/) (2022)
- [MAE-AST: Masked Autoencoding Audio Spectrogram Transformer](https://mlsanity.com/paper/2203.16691/) (2022)
- [Masked Spectrogram Prediction For Self-Supervised Audio Pre-Training](https://mlsanity.com/paper/2204.12768/) (2022)
- [Rethinking CNN Models for Audio Classification](https://mlsanity.com/paper/2007.11154/) (2020)
- [Epic-Sounds: A Large-scale Dataset of Actions That Sound](https://mlsanity.com/paper/2302.00646/) (2023)
- [PEFT for Speech: Unveiling Optimal Placement, Merging Strategies, and Ensemble Techniques](https://mlsanity.com/paper/2401.02122/) (2024)

## Abstract (arXiv)

Recent studies show that pretrained vision models can boost performance in audio downstream tasks. To enhance the performance further, an additional pretraining stage with large scale audio data is typically required to infuse audio specific knowledge into the vision model. However, such approaches require extensive audio data and a carefully designed objective function. In this work, we propose bypassing the pretraining stage by directly fine-tuning the vision model with our Look Aside Adapter (LoAA) designed for efficient audio understanding. Audio spectrum data is represented across two heterogeneous dimensions time and frequency and we refine adapters to facilitate interactions between tokens across these dimensions. Our experiments demonstrate that our adapters allow vision models to reach or surpass the performance of pretrained audio models in various audio and speech tasks, offering a resource efficient and effective solution for leveraging vision models in audio applications.