Is Generative Modeling-based Stylization Necessary for Domain Adaptation in Regression Tasks?

by   Jinman Park, et al.

Unsupervised domain adaptation (UDA) aims to bridge the gap between source and target domains in the absence of target domain labels using two main techniques: input-level alignment (such as generative modeling and stylization) and feature-level alignment (which matches the distribution of the feature maps, e.g. gradient reversal layers). Motivated from the success of generative modeling for image classification, stylization-based methods were recently proposed for regression tasks, such as pose estimation. However, use of input-level alignment via generative modeling and stylization incur additional overhead and computational complexity which limit their use in real-world DA tasks. To investigate the role of input-level alignment for DA, we ask the following question: Is generative modeling-based stylization necessary for visual domain adaptation in regression? Surprisingly, we find that input-alignment has little effect on regression tasks as compared to classification. Based on these insights, we develop a non-parametric feature-level domain alignment method – Implicit Stylization (ImSty) – which results in consistent improvements over SOTA regression task, without the need for computationally intensive stylization and generative modeling. Our work conducts a critical evaluation of the role of generative modeling and stylization, at a time when these are also gaining popularity for domain generalization.


page 4

page 7


VDM-DA: Virtual Domain Modeling for Source Data-free Domain Adaptation

Domain adaptation aims to leverage a label-rich domain (the source domai...

Instance Level Affinity-Based Transfer for Unsupervised Domain Adaptation

Domain adaptation deals with training models using large scale labeled d...

Revisiting Deep Subspace Alignment for Unsupervised Domain Adaptation

Unsupervised domain adaptation (UDA) aims to transfer and adapt knowledg...

Unsupervised Domain Adaptation with Copula Models

We study the task of unsupervised domain adaptation, where no labeled da...

Manifold-Aware Self-Training for Unsupervised Domain Adaptation on Regressing 6D Object Pose

Domain gap between synthetic and real data in visual regression (6D pose...

A Compact DNN: Approaching GoogLeNet-Level Accuracy of Classification and Domain Adaptation

Recently, DNN model compression based on network architecture design, e....

Please sign up or login with your details

Forgot password? Click here to reset