https://github.com/peizesun/vlpart

https://github.com/peizesun/vlpart

Last synced: 6 months ago
JSON representation

• Host: GitHub
• URL: https://github.com/peizesun/vlpart
• Owner: PeizeSun
• License: mit
• Created: 2023-03-16T11:12:52.000Z (over 3 years ago)
• Default Branch: main
• Last Pushed: 2023-05-15T00:15:01.000Z (about 3 years ago)
• Last Synced: 2025-06-18T23:41:04.776Z (about 1 year ago)
• Size: 10.9 MB
• Stars: 1
• Watchers: 2
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

          
# Model Checkpoints for [VLPart](https://github.com/facebookresearch/VLPart)

![](docs/boom.png)

Object detection has been expanded from a limited number of categories to open vocabulary. 

Moving forward, a complete intelligent vision system requires understanding more fine-grained object descriptions, object parts. 

In this work, we propose a detector with the ability to predict both open-vocabulary objects and their part segmentation.

This ability comes from two designs:

- We train the detector on the joint of part-level, object-level and image-level data. 

- We parse the novel object into its parts by its dense semantic correspondence with the base object.