Supervised Domain Adaptation: A Graph Embedding Perspective and a Rectified Experimental Protocol

Abstract

Domain Adaptation is the process of alleviating distribution gaps between data from different domains. In this paper, we show that Domain Adaptation methods using pair-wise relationships between source and target domain data can be formulated as a Graph Embedding in which the domain labels are incorporated into the structure of the intrinsic and penalty graphs. Specifically, we analyse the loss functions of three existing state-of-the-art Supervised Domain Adaptation methods and demonstrate that they perform Graph Embedding. Moreover, we highlight some generalisation and reproducibility issues related to the experimental setup commonly used to demonstrate the few-shot learning capabilities of these methods. To assess and compare Supervised Domain Adaptation methods accurately, we propose a rectified evaluation protocol, and report updated benchmarks on the standard datasets Office31 (Amazon, DSLR, and Webcam), Digits (MNIST, USPS, SVHN, and MNIST-M) and VisDA (Synthetic, Real).

13 pages, 7 figures, 6 tables

References in corpus (7)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• A Tutorial on Bayesian Optimization of Expensive Cost Functions, with Application to Active User Modeling and Hierarchical Reinforcement Learning
• A Closer Look at Memorization in Deep Networks
• An introduction to domain adaptation and transfer learning
• Few-Shot Adversarial Domain Adaptation
• Dimensionality Reduction using Similarity-induced Embeddings
• $d$-SNE: Domain Adaptation using Stochastic Neighborhood Embedding

Cited by in corpus (2)

• Bridging the gap: Towards an Expanded Toolkit for AI-driven Decision-Making in the Public Sector
• Unsupervised Domain Adaptation for Constraining Star Formation Histories