# Unsupervised vs. transfer learning for multimodal one-shot matching of speech and images

arXiv: https://arxiv.org/abs/2008.06258 · HTML: https://mlsanity.com/paper/2008.06258/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Aug 2020.

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

- [Attention-Based Keyword Localisation in Speech using Visual Grounding](https://mlsanity.com/paper/2106.08859/) (2021)
- [YFACC: A Yor`ub'a speech-image dataset for cross-lingual keyword localisation through visual grounding](https://mlsanity.com/paper/2210.04600/) (2022)
- [Keyword localisation in untranscribed speech using visually grounded speech models](https://mlsanity.com/paper/2202.01107/) (2022)
- [Towards visually prompted keyword localisation for zero-resource spoken languages](https://mlsanity.com/paper/2210.06229/) (2022)
- [Visually grounded few-shot word learning in low-resource settings](https://mlsanity.com/paper/2306.11371/) (2023)
- [Visually grounded few-shot word acquisition with fewer shots](https://mlsanity.com/paper/2305.15937/) (2023)
- [A Multiple Classifier Approach for Concatenate-Designed Neural Networks](https://mlsanity.com/paper/2101.05457/) (2021)

## Abstract (arXiv)

We consider the task of multimodal one-shot speech-image matching. An agent is shown a picture along with a spoken word describing the object in the picture, e.g. cookie, broccoli and ice-cream. After observing one paired speech-image example per class, it is shown a new set of unseen pictures, and asked to pick the "ice-cream". Previous work attempted to tackle this problem using transfer learning: supervised models are trained on labelled background data not containing any of the one-shot classes. Here we compare transfer learning to unsupervised models trained on unlabelled in-domain data. On a dataset of paired isolated spoken and visual digits, we specifically compare unsupervised autoencoder-like models to supervised classifier and Siamese neural networks. In both unimodal and multimodal few-shot matching experiments, we find that transfer learning outperforms unsupervised training. We also present experiments towards combining the two methodologies, but find that transfer learning still performs best (despite idealised experiments showing the benefits of unsupervised learning).