Comments (3)
Hello. We have a follow-up work https://arxiv.org/abs/1905.12698 that describes how to implement CEM for colored images with monotonic attribution functions. You can find a notebook demo here: https://nbviewer.jupyter.org/github/IBM/AIX360/blob/master/examples/contrastive/CEM-MAF-CelebA.ipynb
from contrastive-explanation-method.
Thank you. If I understand correctly, the paper mentioned above helps when the colored images have defined attributes. I'm more interested in classification tasks for colored images. Example: Explaining the decision for an image from the imagenet or cifar10 dataset.
from contrastive-explanation-method.
Hello @vikranth94. You are right that we propose the use of attribute features as well as a plug-in generator to generate meaningful contrastive explanations for color images. Note that the attribute features need not be pre-defined and can be self-learned from the datasets (see the "ISIC Lesion dataset" examples in our paper https://arxiv.org/pdf/1905.12698.pdf). For ImageNet and Cifar10 (and other color image datasets), you can plug in pre-trained generators for your purpose.
from contrastive-explanation-method.
Related Issues (4)
- Non NN Black Box Methods HOT 3
- How to define X/X_0? HOT 1
- Software requirements HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from contrastive-explanation-method.