CVDec 13, 2018

DLOW: Domain Flow for Adaptation and Generalization

arXiv:1812.05418v2398 citationsHas Code
Originality Incremental advance
AI Analysis

This addresses the problem of domain shift in computer vision for tasks like semantic segmentation, offering a method to smooth transitions between domains, though it is incremental as it builds on CycleGAN.

The paper tackles domain adaptation and generalization by generating a continuous sequence of intermediate domains to bridge source and target domains, easing adaptation and enabling style generalization, with demonstrated effectiveness on benchmark datasets for cross-domain semantic segmentation.

In this work, we present a domain flow generation(DLOW) model to bridge two different domains by generating a continuous sequence of intermediate domains flowing from one domain to the other. The benefits of our DLOW model are two-fold. First, it is able to transfer source images into different styles in the intermediate domains. The transferred images smoothly bridge the gap between source and target domains, thus easing the domain adaptation task. Second, when multiple target domains are provided for training, our DLOW model is also able to generate new styles of images that are unseen in the training data. We implement our DLOW model based on CycleGAN. A domainness variable is introduced to guide the model to generate the desired intermediate domain images. In the inference phase, a flow of various styles of images can be obtained by varying the domainness variable. We demonstrate the effectiveness of our model for both cross-domain semantic segmentation and the style generalization tasks on benchmark datasets. Our implementation is available at https://github.com/ETHRuiGong/DLOW.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes