DeepAI
Log In Sign Up

Cooperative Distribution Alignment via JSD Upper Bound

07/05/2022
by   Wonwoong Cho, et al.
0

Unsupervised distribution alignment estimates a transformation that maps two or more source distributions to a shared aligned distribution given only samples from each distribution. This task has many applications including generative modeling, unsupervised domain adaptation, and socially aware learning. Most prior works use adversarial learning (i.e., min-max optimization), which can be challenging to optimize and evaluate. A few recent works explore non-adversarial flow-based (i.e., invertible) approaches, but they lack a unified perspective and are limited in efficiently aligning multiple distributions. Therefore, we propose to unify and generalize previous flow-based approaches under a single non-adversarial framework, which we prove is equivalent to minimizing an upper bound on the Jensen-Shannon Divergence (JSD). Importantly, our problem reduces to a min-min, i.e., cooperative, problem and can provide a natural evaluation metric for unsupervised distribution alignment. We present empirical results of our framework on both simulated and real-world datasets to demonstrate the benefits of our approach.

READ FULL TEXT
02/27/2021

Uncertainty-Aware Unsupervised Domain Adaptation in Object Detection

Unsupervised domain adaptive object detection aims to adapt detectors fr...
04/15/2021

Iterative Barycenter Flows

The task of mapping two or more distributions to a shared representation...
03/26/2020

Log-Likelihood Ratio Minimizing Flows: Towards Robust and Quantifiable Neural Distribution Alignment

Unsupervised distribution alignment has many applications in deep learni...
07/13/2017

Stable Distribution Alignment Using the Dual of the Adversarial Distance

Methods that align distributions by minimizing an adversarial distance b...
10/03/2019

A General Upper Bound for Unsupervised Domain Adaptation

In this work, we present a novel upper bound of target error to address ...
02/23/2019

Unsupervised Visual Domain Adaptation: A Deep Max-Margin Gaussian Process Approach

In unsupervised domain adaptation, it is widely known that the target do...
08/15/2019

Domain-adversarial Network Alignment

Network alignment is a critical task to a wide variety of fields. Many e...