Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2505.20872 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909624944295936 |
|---|---|
| author | Zhao, Antony Proshkin, Alex Hennessy, Fergal Crivelli, Francesco |
| author_facet | Zhao, Antony Proshkin, Alex Hennessy, Fergal Crivelli, Francesco |
| contents | Large transformer models have been shown to be capable of performing in-context learning. By using examples in a prompt as well as a query, they are capable of performing tasks such as few-shot, one-shot, or zero-shot learning to output the corresponding answer to this query. One area of interest to us is that these transformer models have been shown to be capable of learning the general class of certain functions, such as linear functions and small 2-layer neural networks, on random data (Garg et al, 2023). We aim to extend this to the image space to analyze their capability to in-context learn more complex functions on the image space, such as convolutional neural networks and other methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_20872 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | In Context Learning with Vision Transformers: Case Study Zhao, Antony Proshkin, Alex Hennessy, Fergal Crivelli, Francesco Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning I.2.6; I.2.10; I.4.8 Large transformer models have been shown to be capable of performing in-context learning. By using examples in a prompt as well as a query, they are capable of performing tasks such as few-shot, one-shot, or zero-shot learning to output the corresponding answer to this query. One area of interest to us is that these transformer models have been shown to be capable of learning the general class of certain functions, such as linear functions and small 2-layer neural networks, on random data (Garg et al, 2023). We aim to extend this to the image space to analyze their capability to in-context learn more complex functions on the image space, such as convolutional neural networks and other methods. |
| title | In Context Learning with Vision Transformers: Case Study |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning I.2.6; I.2.10; I.4.8 |
| url | https://arxiv.org/abs/2505.20872 |