Downloads · 30 days
0
atc_tiny-coco-complete
joakimbh/atc_tiny-coco-complete
atc_tiny-coco-complete 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.
Agglomerative Token Clustering (ATC), a novel hierarchical hard-merging based token reduction method.
Access
Public
Updated Sep 19, 2024
Repo size
178 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pth178 MB · 100%
At a glance
- License
- mit
- Access
- Public
- Created
- Sep 18, 2024
- Updated
- Sep 19, 2024
- SHA
- 8d2eabde
Model card
From the Hugging Face model README
Fine-Tuned Agglomerative Token Clustering - DeiT-Tiny-Complete - COCO 2014
Model Details
Agglomerative Token Clustering (ATC), a novel hierarchical hard-merging based token reduction method.
- Developed by: Joakim Bruslund Haurum, Sergio Escalera, Graham W. Taylor, and Thomas B. Moeslund
- Model type: Vision Transformer
- License: MIT
- Task: Image Classification
Model Card
- Backbone: DeiT-Tiny
- Token Reduction Method: ATC
- Linkage Function: Complete
- 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
Use
The model files contain both standard and EMA model parameters. The version which gave the best performance is indicated with the "ema_best" boolean.
- License
- mit
- Languages
- en
- Created
- Sep 18, 2024
- Updated
- Sep 19, 2024