Journal
2017 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV)
Volume -, Issue -, Pages 5716-5726Publisher
IEEE
DOI: 10.1109/ICCV.2017.609
Keywords
-
Funding
- Center for Identification Technology Research
- National Science Foundation [1066197]
- Direct For Computer & Info Scie & Enginr [1066197] Funding Source: National Science Foundation
- Division Of Computer and Network Systems [1066197] Funding Source: National Science Foundation
Ask authors/readers for more resources
This work provides a unified framework for addressing the problem of visual supervised domain adaptation and generalization with deep models. The main idea is to exploit the Siamese architecture to learn an embedding subspace that is discriminative, and where mapped visual domains are semantically aligned and yet maximally separated. The supervised setting becomes attractive especially when only few target data samples need to be labeled. In this scenario, alignment and separation of semantic probability distributions is difficult because of the lack of data. We found that by reverting to point-wise surrogates of distribution distances and similarities provides an effective solution. In addition, the approach has a high speed of adaptation, which requires an extremely low number of labeled target training samples, even one per category can be effective. The approach is extended to domain generalization. For both applications the experiments show very promising results.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available