rajeevyasarla / 3sd Goto Github PK
View Code? Open in Web Editor NEW3SD: Self-Supervised Saliency Detection With No Labels
License: MIT License
3SD: Self-Supervised Saliency Detection With No Labels
License: MIT License
edge maps are computed using pretrained RCF : https://github.com/yun-liu/rcf
Originally posted by @rajeevyasarla in #1 (comment)
Sorry to open a new issue.
Does the 'pretrained RCF' mean the model trained on the BSDS500 which is labelled by humans?
I note that in "basenet_train.py", the saliency GT label is used in losses , is it different from paper?
Hi there. Thanks for your excellent work for USOD!
I'm wondering how you define the param weights of RCFNet for edge extraction. Is it loaded from pretrained or trained from scratch every time?
Nice Work. In the code you get the cam_map using only one Conv2d layer. According to my intuition, here should not use a method like GradCAM to get CAM. And I also see this process in other place. Can you explain why this this works? Thank you.
thank you for your nice work❤️. but what about the compute_metrics.py code?
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.