xiuqhou/Salience-DETR

[CVPR 2024] Official implementation of the paper "Salience DETR: Enhancing Detection Transformer with Hierarchical Salience Filtering Refinement"

39
/ 100
Emerging

This project helps computer vision practitioners accurately identify and locate objects within images, even for very small or irregularly shaped items. You provide an image with various objects, and it precisely draws bounding boxes around each object, including fine details of their outlines. This is ideal for quality control specialists, automated inspection engineers, or anyone building systems for visual recognition.

225 stars. No commits in the last 6 months.

Use this if you need highly precise object detection, especially for tasks involving small objects or when capturing the exact contours of an object is important for analysis.

Not ideal if you only need general object recognition without high precision bounding box or contour detection, or if you're not working with visual data.

automated-inspection quality-control defect-detection image-analysis visual-recognition
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 13 / 25

How are scores calculated?

Stars

225

Forks

17

Language

Jupyter Notebook

License

Apache-2.0

Last pushed

Apr 11, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/xiuqhou/Salience-DETR"

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