noelshin/selfmask
[CVPRW'22] Unsupervised Salient Object Detection With Spectral Cluster Voting
This project helps you automatically identify and highlight the most prominent object in any image without needing manually labeled examples. It takes your input images and generates precise 'pseudo-masks' that outline the main subject, making it easier to isolate or analyze. Anyone working with visual content, such as content creators, e-commerce managers, or researchers, can use this to quickly pinpoint key elements in their photos.
No commits in the last 6 months.
Use this if you need to automatically select the most visually important object in a collection of images, especially when you don't have human-annotated examples to train a system.
Not ideal if you need to detect multiple specific objects, or if the 'salient' object is subjective or requires complex contextual understanding rather than pure visual prominence.
Stars
65
Forks
6
Language
Python
License
MIT
Category
Last pushed
Apr 20, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/noelshin/selfmask"
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,...