ananthu-aniraj/pdiscoformer

[ECCV 2024 Oral] Official implementation of the paper "PDiscoFormer: Relaxing Part Discovery Constraints with Vision Transformers"

29
/ 100
Experimental

This project helps computer vision researchers and practitioners automatically identify the distinct parts of objects within images, like the wings of a bird or the petals of a flower. It takes an image as input and outputs a segmented image highlighting the discovered object parts, along with a classification of the main object. This is for those working on fine-grained image classification or developing more interpretable AI models.

No commits in the last 6 months.

Use this if you need to precisely understand and classify objects by their constituent parts, especially when those parts might have complex shapes or be spread out.

Not ideal if you only need a simple, overall classification of an image without detailed part identification or if you require real-time processing on very limited hardware.

fine-grained classification image segmentation object part detection interpretable AI computer vision research
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 6 / 25
Maturity 16 / 25
Community 5 / 25

How are scores calculated?

Stars

18

Forks

1

Language

Python

License

MIT

Last pushed

Jul 03, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/ananthu-aniraj/pdiscoformer"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.