|
--- |
|
pipeline_tag: image-classification |
|
tags: |
|
- image-classification |
|
license: mit |
|
datasets: |
|
- efekankavalci/CUB_200_2011 |
|
language: |
|
- en |
|
base_model: |
|
- timm/vit_base_patch14_reg4_dinov2.lvd142m |
|
--- |
|
|
|
# PdiscoFormer CUB Model (K=8) |
|
|
|
PdiscoFormer (Vit-base-dinov2-reg4) trained on CUB with K (number of unsupervised parts to discover) set to a value of 8. |
|
|
|
|
|
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}, |
|
} |
|
``` |
