A Two-Step Disentanglement Method

September 01, 2017 · Entered Twilight · 🏛 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition

"Last commit was 7.0 years ago (≥5 year threshold)"

Evidence collected by the PWNC Scanner

Repo contents: DisAdvNet.py, DisAdvNet2.py, README.md, data, models, test_net.py, train_proc.py

Authors Naama Hadad, Lior Wolf, Moni Shahar arXiv ID 1709.00199 Category cs.LG: Machine Learning Cross-listed stat.ML Citations 84 Venue 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Repository https://github.com/naamahadad/A-Two-Step-Disentanglement-Method ⭐ 21 Last Checked 1 month ago

Abstract

We address the problem of disentanglement of factors that generate a given data into those that are correlated with the labeling and those that are not. Our solution is simpler than previous solutions and employs adversarial training. First, the part of the data that is correlated with the labels is extracted by training a classifier. Then, the other part is extracted such that it enables the reconstruction of the original data but does not contain label information. The utility of the new method is demonstrated on visual datasets as well as on financial data. Our code is available at https://github.com/naamahadad/A-Two-Step-Disentanglement-Method