Language selection

Government of Canada / Gouvernement du Canada

Search

Source-free unsupervised domain adaptation with surrogate data generation

From National Research Council Canada

Download
  1. (PDF, 545 KiB)
AuthorSearch for: ; Search for: ; Search for: 1
Affiliation
  1. National Research Council of Canada. Digital Technologies
FormatText, Article
ConferenceThe 32nd British Machine Vision Conference, Nov. 22-25, 2021, Virtual Conference
Physical description12 p.
Abstract
Source-free unsupervised domain adaptation aims to learn a model that generalizes well on a target domain given the pre-trained source model and unlabeled target data. Traditional unsupervised domain adaptation methods are mostly not applicable to this setting since no source data are available. To tackle this problem, we propose to generate labeled surrogate source training data from the source model by fixing the model and optimizing the inputs. To avoid naive local fittings to individual instances and in light of the model optimization process, we further enforce model gradient based global fitting constraints on the whole dataset generation and solve the formulated optimization problem using an ADMM algorithm. The generated labeled source training data can then be used to deploy existing unsupervised domain adaptation methods. Furthermore, we propose to incorporate the unlabeled target data into the domain adaptation process to improve generalization in the target domain with a mutual information loss. Experiments show that our proposed method can achieve the state-of-the-art results on benchmark datasets.
Publication date
PublisherBritish Machine Vision Association UK
In
  • BMVC 2021 - British Machine Vision Conference (25 November 2021).
LanguageEnglish
Peer reviewedYes
Export citationExport as RIS
Report a correctionReport a correction (opens in a new tab)
Record identifier9aa7da1b-43e7-4a9f-989c-821c3ff46464
Record created2022-02-16
Record modified2022-02-16
Date modified: