README.md

metadata

pipeline_tag: image-classification
tags:
  - model_hub_mixin
  - pytorch_model_hub_mixin
  - image-classification
license: mit
language:
  - en
base_model:
  - timm/vit_base_patch14_reg4_dinov2.lvd142m

PdiscoFormer NABirds Model (K=4)

PdiscoFormer (Vit-base-dinov2-reg4) trained on NABirds with K (number of unsupervised parts to discover) set to a value of 4.

PdiscoFormer is a novel method for unsupervised part discovery using self-supervised Vision Transformers which achieves state-of-the-art results for this task, both qualitatively and quantitatively. The code can be found in the following repository: https://github.com/ananthu-aniraj/pdiscoformer

BibTex entry and citation info

@misc{aniraj2024pdiscoformerrelaxingdiscoveryconstraints,
      title={PDiscoFormer: Relaxing Part Discovery Constraints with Vision Transformers}, 
      author={Ananthu Aniraj and Cassio F. Dantas and Dino Ienco and Diego Marcos},
      year={2024},
      eprint={2407.04538},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2407.04538}, 
}]