teddykoker / u-noise Goto Github PK
View Code? Open in Web Editor NEWOfficial PyTorch code for U-Noise: Learnable Noise Masks for Interpretable Image Segmentation (ICIP 2021)
Home Page: https://arxiv.org/abs/2101.05791
Official PyTorch code for U-Noise: Learnable Noise Masks for Interpretable Image Segmentation (ICIP 2021)
Home Page: https://arxiv.org/abs/2101.05791
Hello! First of all great work. While running train_noise pretrained I ran into a problem where the keys in state_dict were wrong. For example, the keys should be something like "model.downs.0.0.weight", but its giving me an error saying my keys were "util_model.model.downs.0.0.weight". I am running this on Python 3.8, was this error due to a different Python version?
I've tried many times, but the web page reminds me of a network error, or the connection is always down
Dear Teddy Koker @teddykoker and co-authors,
I would like to kindly ask you to revise the citations and update the arxiv version of your paper.
[6] Vinogradova, K., Dibrov, A., & Myers, G. (2020). Towards Interpretable Semantic Segmentation via Gradient-Weighted Class Activation Mapping (Student Abstract). Proceedings of the AAAI Conference on Artificial Intelligence, 34(10), 13943-13944. https://doi.org/10.1609/aaai.v34i10.7244
They either return explanations for a part of the image [6, 7] or for a single pixel [6] or for the whole class [6].
In :
"There are only a few previous works that focus on segmentation interpretability [6, 7]. These works solve the problem in
a lower resolution setup, and then up-sample to get pixel level explanation. They also only return explanations with respect
to a single pixel [ 6] or a part of the image [7]. "
"Finally, for Grad-CAM, we follow [ 6, 11 ] and obtain a heatmap with respect to the convolutional layer at the bottleneck of the Utility model."
Seg-Grad-CAM, the method proposed in my peer-reviewed publication, takes the gradients with respect to the convolutional layer at the bottleneck of the U-Net and produces explanations for a) single pixel, b) class mask (all pixels belonging to the class), c) ROI (e.g. an instance).
I would really appreciate it and cite your paper in my current work.
Kind regards,
Kira
Hi! Thank you for sharing your great work! When I was studying make_ visualizations. py, I met some problems.
You define activations_ hook on line 21 of the program, but line 22 self.gradients = grads is not really initialized. So I found 36 lines of self activations_ hook will not call the function of line 21, which leads to errors in subsequent programs.
Therefore, do you have a good way to solve this problem or can you provide the latest version of the code?
Thank you very much and look forward to your reply! Best regards!
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ 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. ๐๐๐
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 โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.