akshitac8/OW-DETR
[CVPR 2022] Official Pytorch code for OW-DETR: Open-world Detection Transformer
This tool helps automate the identification of objects in images, even when those objects haven't been explicitly shown to the system before. You feed it a collection of images, and it can detect both objects it recognizes and highlight entirely new, unknown objects within those images. This is useful for professionals in fields like surveillance, quality control, or scientific imaging who need to continuously monitor and identify both expected and unexpected items.
257 stars. No commits in the last 6 months.
Use this if you need an object detection system that can not only identify known items but also dynamically learn and recognize new, previously unseen objects over time without requiring a full system rebuild.
Not ideal if your object detection needs are limited to a fixed set of known categories and you do not anticipate encountering novel objects.
Stars
257
Forks
47
Language
Python
License
—
Category
Last pushed
Apr 04, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/akshitac8/OW-DETR"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
dddzg/up-detr
[TPAMI 2022 & CVPR2021 Oral] UP-DETR: Unsupervised Pre-training for Object Detection with Transformers
hanouticelina/deformable-DETR
Implementation of the paper : Deformable DETR: Deformable Transformers for End-to-End Object...
xiuqhou/Relation-DETR
[ECCV2024 Oral] Official implementation of the paper "Relation DETR: Exploring Explicit Position...
xiuqhou/Salience-DETR
[CVPR 2024] Official implementation of the paper "Salience DETR: Enhancing Detection Transformer...
BarCodeReader/SelfReformer
[TMM-2023] Official implementation of "Towards Complete and Detail-Preserved Salient Object...