2016/11/24 by Piotr Koniusz, Koniusz, Piotr, Yusuf Tas +3 · 2 citations
Computer Science · #Computer Vision and Pattern Recognition (cs.CV) #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Speech and Audio Processing #Video Surveillance and Tracking Methods #cs.CV
paper · pdf · doi:10.48550/arxiv.1611.08195
CVPR'17
openalex publication_date 2016/11/24 · arxiv created 2017/04/11 · arxiv updated 2017/04/12 · openalex created_date 2022/10/03 · openalex updated_date 2026/07/28
In this paper, we propose an approach to the domain adaptation, dubbed Second- or Higher-order Transfer of Knowledge (So-HoT), based on the mixture of alignments of second- or higher-order scatter statistics between the source and target domains. The human ability to learn from few labeled samples is a recurring motivation in the literature for domain adaptation. Towards this end, we investigate the supervised target scenario for which few labeled target training samples per category exist. Specifically, we utilize two CNN streams: the source and target networks fused at the classifier level. Features from the fully connected layers fc7 of each network are used to compute second- or even higher-order scatter tensors; one per network stream per class. As the source and target distributions are somewhat different despite being related, we align the scatters of the two network streams of the same class (within-class scatters) to a desired degree with our bespoke loss while maintaining good separation of the between-class scatters. We train the entire network in end-to-end fashion. We provide evaluations on the standard Office benchmark (visual domains), RGB-D combined with Caltech256 (depth-to-rgb transfer) and Pascal VOC2007 combined with the TU Berlin dataset (image-to-sketch transfer). We attain state-of-the-art results.