Beyond Sharing Weights for Deep Domain Adaptation

03/21/2016
by   Artem Rozantsev, et al.
0

The performance of a classifier trained on data coming from a specific domain typically degrades when applied to a related but different one. While annotating many samples from the new domain would address this issue, it is often too expensive or impractical. Domain Adaptation has therefore emerged as a solution to this problem; It leverages annotated data from a source domain, in which it is abundant, to train a classifier to operate in a target domain, in which it is either sparse or even lacking altogether. In this context, the recent trend consists of learning deep architectures whose weights are shared for both domains, which essentially amounts to learning domain invariant features. Here, we show that it is more effective to explicitly model the shift from one domain to the other. To this end, we introduce a two-stream architecture, where one operates in the source domain and the other in the target domain. In contrast to other approaches, the weights in corresponding layers are related but not shared. We demonstrate that this both yields higher accuracy than state-of-the-art methods on several object recognition and detection tasks and consistently outperforms networks with shared weights in both supervised and unsupervised settings.

READ FULL TEXT

page 1

page 4

page 7

page 8

research
05/25/2020

Contradistinguisher: Applying Vapnik's Philosophy to Unsupervised Domain Adaptation

A complex combination of simultaneous supervised-unsupervised learning i...
research
11/21/2017

Residual Parameter Transfer for Deep Domain Adaptation

The goal of Deep Domain Adaptation is to make it possible to use Deep Ne...
research
09/29/2020

Tackling unsupervised multi-source domain adaptation with optimism and consistency

It has been known for a while that the problem of multi-source domain ad...
research
02/24/2018

Adaptive Deep Learning through Visual Domain Localization

A commercial robot, trained by its manufacturer to recognize a predefine...
research
03/14/2022

CheckSel: Efficient and Accurate Data-valuation Through Online Checkpoint Selection

Data valuation and subset selection have emerged as valuable tools for a...
research
08/05/2019

Image to Video Domain Adaptation Using Web Supervision

Training deep neural networks typically requires large amounts of labele...
research
08/22/2014

Hierarchical Adaptive Structural SVM for Domain Adaptation

A key topic in classification is the accuracy loss produced when the dat...

Please sign up or login with your details

Forgot password? Click here to reset