Efficient Vision-Language Pre-training by Cluster Masking
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866913350566281216 |
|---|---|
| author | Wei, Zihao Pan, Zixuan Owens, Andrew |
| author_facet | Wei, Zihao Pan, Zixuan Owens, Andrew |
| contents | We propose a simple strategy for masking image patches during visual-language contrastive learning that improves the quality of the learned representations and the training speed. During each iteration of training, we randomly mask clusters of visually similar image patches, as measured by their raw pixel intensities. This provides an extra learning signal, beyond the contrastive training itself, since it forces a model to predict words for masked visual structures solely from context. It also speeds up training by reducing the amount of data used in each image. We evaluate the effectiveness of our model by pre-training on a number of benchmarks, finding that it outperforms other masking strategies, such as FLIP, on the quality of the learned representation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_08815 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Efficient Vision-Language Pre-training by Cluster Masking Wei, Zihao Pan, Zixuan Owens, Andrew Computer Vision and Pattern Recognition We propose a simple strategy for masking image patches during visual-language contrastive learning that improves the quality of the learned representations and the training speed. During each iteration of training, we randomly mask clusters of visually similar image patches, as measured by their raw pixel intensities. This provides an extra learning signal, beyond the contrastive training itself, since it forces a model to predict words for masked visual structures solely from context. It also speeds up training by reducing the amount of data used in each image. We evaluate the effectiveness of our model by pre-training on a number of benchmarks, finding that it outperforms other masking strategies, such as FLIP, on the quality of the learned representation. |
| title | Efficient Vision-Language Pre-training by Cluster Masking |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2405.08815 |