RADIOv2.5: Improved Baselines for Agglomerative Vision Foundation Models
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913684440219648 |
|---|---|
| author | Heinrich, Greg Ranzinger, Mike Hongxu Yin Lu, Yao Kautz, Jan Tao, Andrew Catanzaro, Bryan Molchanov, Pavlo |
| author_facet | Heinrich, Greg Ranzinger, Mike Hongxu Yin Lu, Yao Kautz, Jan Tao, Andrew Catanzaro, Bryan Molchanov, Pavlo |
| contents | Agglomerative models have recently emerged as a powerful approach to training vision foundation models, leveraging multi-teacher distillation from existing models such as CLIP, DINO, and SAM. This strategy enables the efficient creation of robust models, combining the strengths of individual teachers while significantly reducing computational and resource demands. In this paper, we thoroughly analyze state-of-the-art agglomerative models, identifying critical challenges including resolution mode shifts, teacher imbalance, idiosyncratic teacher artifacts, and an excessive number of output tokens. To address these issues, we propose several novel solutions: multi-resolution training, mosaic augmentation, and improved balancing of teacher loss functions. Specifically, in the context of Vision Language Models, we introduce a token compression technique to maintain high-resolution information within a fixed token count. We release our top-performing variants at multiple scales (-B, -L, -H, and -g), along with inference code and pretrained weights |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_07679 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | RADIOv2.5: Improved Baselines for Agglomerative Vision Foundation Models Heinrich, Greg Ranzinger, Mike Hongxu Yin Lu, Yao Kautz, Jan Tao, Andrew Catanzaro, Bryan Molchanov, Pavlo Computer Vision and Pattern Recognition Artificial Intelligence Agglomerative models have recently emerged as a powerful approach to training vision foundation models, leveraging multi-teacher distillation from existing models such as CLIP, DINO, and SAM. This strategy enables the efficient creation of robust models, combining the strengths of individual teachers while significantly reducing computational and resource demands. In this paper, we thoroughly analyze state-of-the-art agglomerative models, identifying critical challenges including resolution mode shifts, teacher imbalance, idiosyncratic teacher artifacts, and an excessive number of output tokens. To address these issues, we propose several novel solutions: multi-resolution training, mosaic augmentation, and improved balancing of teacher loss functions. Specifically, in the context of Vision Language Models, we introduce a token compression technique to maintain high-resolution information within a fixed token count. We release our top-performing variants at multiple scales (-B, -L, -H, and -g), along with inference code and pretrained weights |
| title | RADIOv2.5: Improved Baselines for Agglomerative Vision Foundation Models |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2412.07679 |