---
language: en
license: mit
tags:
- atc
---

# Fine-Tuned Agglomerative Token Clustering - DeiT-Base-Complete - ImageNet-1k

### 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-Base
- **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](https://github.com/JoakimHaurum/ATC)
- **Paper:** [https://arxiv.org/abs/2409.11923](https://arxiv.org/abs/2409.11923)
- **Project Page:** [https://vap.aau.dk/atc](https://vap.aau.dk/atc)
- **HuggingFace Collection:** [https://huggingface.co/collections/joakimbh/agglomerative-token-clustering-66e94dfb313e85ec97590fe4](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.