Co-Learning with Pre-Trained Networks Improves Source-Free Domain Adaptation

12/15/2022
by   Wenyu Zhang, et al.
0

Source-free domain adaptation aims to adapt a source model trained on fully-labeled source domain data to a target domain with unlabeled target domain data. Source data is assumed inaccessible due to proprietary or privacy reasons. Existing works use the source model to pseudolabel target data, but the pseudolabels are unreliable due to data distribution shift between source and target domain. In this work, we propose to leverage an ImageNet pre-trained feature extractor in a new co-learning framework to improve target pseudolabel quality for finetuning the source model. Benefits of the ImageNet feature extractor include that it is not source-biased and it provides an alternate view of features and classification decisions different from the source model. Such pre-trained feature extractors are also publicly available, which allows us to readily leverage modern network architectures that have strong representation learning ability. After co-learning, we sharpen predictions of non-pseudolabeled samples by entropy minimization. Evaluation on 3 benchmark datasets show that our proposed method can outperform existing source-free domain adaptation methods, as well as unsupervised domain adaptation methods which assume joint access to source and target data.

READ FULL TEXT
research
11/21/2019

Improving Unsupervised Domain Adaptation with Variational Information Bottleneck

Domain adaptation aims to leverage the supervision signal of source doma...
research
07/12/2021

Source-Free Adaptation to Measurement Shift via Bottom-Up Feature Restoration

Source-free domain adaptation (SFDA) aims to adapt a model trained on la...
research
10/19/2022

Variational Model Perturbation for Source-Free Domain Adaptation

We aim for source-free domain adaptation, where the task is to deploy a ...
research
09/02/2021

On-target Adaptation

Domain adaptation seeks to mitigate the shift between training on the so...
research
05/24/2022

DistillAdapt: Source-Free Active Visual Domain Adaptation

We present a novel method, DistillAdapt, for the challenging problem of ...
research
07/03/2020

Domain Adaptation without Source Data

Domain adaptation assumes that samples from source and target domains ar...
research
03/07/2019

Unsupervised Domain Adaptation using Feature-Whitening and Consensus Loss

A classifier trained on a dataset seldom works on other datasets obtaine...

Please sign up or login with your details

Forgot password? Click here to reset