13 citations · 19 across the 2 of their papers we have counts for
4 papers
Explanation by Progressive Exaggeration
Sumedha Singla, Brian Pollack, Junxiang Chen +1
As machine learning methods see greater adoption and implementation in high stakes applications such as medical image diagnosis, the need for model interpretability and explanation…
Robust Ordinal VAE: Employing Noisy Pairwise Comparisons for Disentanglement
Junxiang Chen, Kayhan Batmanghelich
Recent work by Locatello et al. (2018) has shown that an inductive bias is required to disentangle factors of interest in Variational Autoencoder (VAE). Motivated by a real-world p…
Weakly Supervised Disentanglement by Pairwise Similarities
Junxiang Chen, Kayhan Batmanghelich
Recently, researches related to unsupervised disentanglement learning with deep generative models have gained substantial popularity. However, without introducing supervision, ther…
Generative-Discriminative Complementary Learning
Yanwu Xu, Mingming Gong, Junxiang Chen +3
Majority of state-of-the-art deep learning methods are discriminative approaches, which model the conditional distribution of labels given inputs features. The success of such appr…