Downloads · 30 days
0
tome_tiny-coco17
joakimbh/tome_tiny-coco17
tome_tiny-coco17 is a machine learning model from joakimbh. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as mit.
Token Merging, a bipartitie matching algorithm for token reduction.
Access
Public
Updated Sep 19, 2024
Repo size
338 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pth338 MB · 100%
At a glance
- License
- mit
- Access
- Public
- Created
- Sep 17, 2024
- Updated
- Sep 19, 2024
- SHA
- b358736d
Model card
From the Hugging Face model README
Fine-Tuned Token Merging - ViT-Adapter-Tiny - COCO 2017
Model Details
Token Merging, a bipartitie matching algorithm for token reduction.
- Developed by: Joakim Bruslund Haurum, Sergio Escalera, Graham W. Taylor, and Thomas B. Moeslund
- Model type: ViT-Adapter
- License: MIT
- Task: Object Detection and Segmentation
Model Card
- Backbone: ViT-Adapter-Tiny
- Token Reduction Method: ToMe
- Reduction Ratio: {0.25, 0.5, 0.7, 0.9}
- Reduction Stages: 3, 6, 9
More Resources
- Repository: https://github.com/JoakimHaurum/ATC
- Paper: https://arxiv.org/abs/2409.11923
- Project Page: https://vap.aau.dk/atc
- HuggingFace Collection: https://huggingface.co/collections/joakimbh/agglomerative-token-clustering-66e94dfb313e85ec97590fe4
- License
- mit
- Languages
- en
- Created
- Sep 17, 2024
- Updated
- Sep 19, 2024