Deep Adversarial Transition Learning using Cross-Grafted Generative Stacks
This addresses the problem of domain shift in computer vision for applications like image classification, but it is incremental as it builds on existing VAE and GAN methods.
The paper tackles domain adaptation in computer vision by introducing a deep adversarial transition learning framework that projects source and target domains into intermediate spaces using cross-grafted generative stacks, achieving state-of-the-art performance on unsupervised benchmarks.
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 "deep adversarial transition learning" (DATL) framework that bridges the domain gap by projecting the source and target domains into intermediate, transitional spaces through the employment of adjustable, cross-grafted generative network stacks and effective adversarial learning between transitions. Specifically, we construct variational auto-encoders (VAE) for the two domains, and form bidirectional transitions by cross-grafting the VAEs' decoder stacks. Furthermore, generative adversarial networks (GAN) are employed for domain adaptation, 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, transitions generation, and transitions alignment by GANs. Experimental results demonstrate that our method outperforms the state-of-the art on a number of unsupervised domain adaptation benchmarks.