Disentanglement Challenge: From Regularization to Reconstruction

TL;DR

This paper improves disentangled representation learning by enhancing FactorVAE's reconstruction capacity and training process, leading to top performance in a real-world dataset challenge.

Contribution

It introduces a method that enhances FactorVAE without new regularization, focusing on better reconstruction and network capacity, achieving first place in the challenge.

Findings

Achieved first place in the disentanglement challenge.

Improved reconstruction performance over baseline methods.

Increased network capacity and training steps enhance disentanglement.

Abstract

The challenge of learning disentangled representation has recently attracted much attention and boils down to a competition using a new real world disentanglement dataset (Gondal et al., 2019). Various methods based on variational auto-encoder have been proposed to solve this problem, by enforcing the independence between the representation and modifying the regularization term in the variational lower bound. However recent work by Locatello et al. (2018) has demonstrated that the proposed methods are heavily influenced by randomness and the choice of the hyper-parameter. In this work, instead of designing a new regularization term, we adopt the FactorVAE but improve the reconstruction performance and increase the capacity of network and the training step. The strategy turns out to be very effective and achieve the 1st place in the challenge.