Discriminative Noise Robust Sparse Orthogonal Label Regression-based Domain Adaptation

Abstract

Domain adaptation (DA) aims to enable a learning model trained from a source domain to generalize well on a target domain, despite the mismatch of data distributions between the two domains. State-of-the-art DA methods have so far focused on the search of a latent shared feature space where source and target domain data can be aligned either statistically and/or geometrically. In this paper, we propose a novel unsupervised DA method, namely Discriminative Noise Robust Sparse Orthogonal Label Regression-based Domain Adaptation (DOLL-DA). The proposed DOLL-DA derives from a novel integrated model which searches a shared feature subspace where source and target domain data are, through optimization of some repulse force terms, discriminatively aligned statistically, while at same time regresses orthogonally data labels thereof using a label embedding trick. Furthermore, in minimizing a novel Noise Robust Sparse Orthogonal Label Regression(NRS_OLR) term, the proposed model explicitly accounts for data outliers to avoid negative transfer and introduces the property of sparsity when regressing data labels. Due to the character restriction. Please read our detailed abstract in our paper.

arXiv comment17figures,17pages. arXiv admin note: text overlap with arXiv:1712.10042

References in corpus (9)

• DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition
• Learning Transferable Features with Deep Adaptation Networks
• Deep Domain Confusion: Maximizing for Domain Invariance
• Domain Separation Networks
• Beyond Sharing Weights for Deep Domain Adaptation
• Optimal Bayesian Transfer Learning
• Multi-source Domain Adaptation for Semantic Segmentation
• Visual and Semantic Knowledge Transfer for Large Scale Semi-supervised Object Detection
• Robust Data Geometric Structure Aligned Close yet Discriminative Domain Adaptation