scuwyh2000/RandBox
[ICCV 2023] PyTorch implementation of RandBox
This project helps computer vision practitioners detect a wide range of objects in images, even those it hasn't been explicitly trained on. You input images, and it outputs bounding box detections and labels for both known and previously unseen objects. This is ideal for vision engineers or AI researchers building robust object detection systems.
No commits in the last 6 months.
Use this if you need an object detection system that can identify new, unexpected objects in an image without needing to be retrained on them.
Not ideal if you only need to detect a fixed set of known objects and prefer a simpler, potentially faster, closed-set detector.
Stars
56
Forks
5
Language
Python
License
—
Category
Last pushed
Nov 04, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/scuwyh2000/RandBox"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
hkchengrex/CascadePSP
[CVPR 2020] CascadePSP: Toward Class-Agnostic and Very High-Resolution Segmentation via Global...
nv-tlabs/GSCNN
Gated-Shape CNN for Semantic Segmentation (ICCV 2019)
lim-anggun/FgSegNet
FgSegNet: Foreground Segmentation Network, Foreground Segmentation Using Convolutional Neural...
jiwoon-ahn/irn
Weakly Supervised Learning of Instance Segmentation with Inter-pixel Relations, CVPR 2019 (Oral)
suyukun666/UFO
Official PyTorch implementation of the “A Unified Transformer Framework for Co-Segmentation,...