Lab's Research: Unsupervised Domain Adaptation using Deep Networks with Cross-Grafted Stacks

Abstract: Current deep domain adaptation methods used in computer vision have mainly focused on learning discriminative and domain-invariant features across different domains. In this paper, we present a novel approach that bridges the domain gap by projecting the source and target domains into a common association space through an unsupervised ``cross-grafted representation stacking'' (CGRS) mechanism. Specifically, we construct variational auto-encoders (VAE) for the two domains, and form bidirectional associations by cross-grafting the VAEs' decoder stacks. Furthermore, generative adversarial networks (GAN) are employed for domain adaptation (DA), mapping the target domain data to the known label space of the source domain. The overall adaptation process hence consists of three phases: feature representation learning by VAEs, association generation, and association alignment by GANs. Experimental results demonstrate that our CGRS-DA approach outperforms the state-of-the-art on a number of unsupervised domain adaptation benchmarks.


Model Scheme:



This research paper was awarded 'The Honourable Mention Paper' at Task-CV 2019@ ICCV. Its extended version was published on Neural Networks

Reference: 
Hou, J.; Ding, X.; Deng, J. D. & Cranefield, S. Unsupervised Domain Adaptation using Deep Networks with Cross-Grafted Stacks IEEE International Conference on Computer Vision Workshop (ICCVW), 2019, 3257-3264

Comments

Popular posts from this blog

Lab's weekly topic - week 50 2023 - Detailed explanation for encoder of U-Net

Lab's recommendation: Awesome books to learn machine learning and AI (continue updating)