Dataset Augmentation by Mixing Visual Concepts
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_ | 1866915072684589056 |
|---|---|
| author | Rahat, Abdullah Al Venkateswara, Hemanth |
| author_facet | Rahat, Abdullah Al Venkateswara, Hemanth |
| contents | This paper proposes a dataset augmentation method by fine-tuning pre-trained diffusion models. Generating images using a pre-trained diffusion model with textual conditioning often results in domain discrepancy between real data and generated images. We propose a fine-tuning approach where we adapt the diffusion model by conditioning it with real images and novel text embeddings. We introduce a unique procedure called Mixing Visual Concepts (MVC) where we create novel text embeddings from image captions. The MVC enables us to generate multiple images which are diverse and yet similar to the real data enabling us to perform effective dataset augmentation. We perform comprehensive qualitative and quantitative evaluations with the proposed dataset augmentation approach showcasing both coarse-grained and finegrained changes in generated images. Our approach outperforms state-of-the-art augmentation techniques on benchmark classification tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_15358 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Dataset Augmentation by Mixing Visual Concepts Rahat, Abdullah Al Venkateswara, Hemanth Computer Vision and Pattern Recognition This paper proposes a dataset augmentation method by fine-tuning pre-trained diffusion models. Generating images using a pre-trained diffusion model with textual conditioning often results in domain discrepancy between real data and generated images. We propose a fine-tuning approach where we adapt the diffusion model by conditioning it with real images and novel text embeddings. We introduce a unique procedure called Mixing Visual Concepts (MVC) where we create novel text embeddings from image captions. The MVC enables us to generate multiple images which are diverse and yet similar to the real data enabling us to perform effective dataset augmentation. We perform comprehensive qualitative and quantitative evaluations with the proposed dataset augmentation approach showcasing both coarse-grained and finegrained changes in generated images. Our approach outperforms state-of-the-art augmentation techniques on benchmark classification tasks. |
| title | Dataset Augmentation by Mixing Visual Concepts |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2412.15358 |