General Domain Adaptation Through Proportional Progressive Pseudo Labeling

by   Mohammad J. Hashemi, et al.

Domain adaptation helps transfer the knowledge gained from a labeled source domain to an unlabeled target domain. During the past few years, different domain adaptation techniques have been published. One common flaw of these approaches is that while they might work well on one input type, such as images, their performance drops when applied to others, such as text or time-series. In this paper, we introduce Proportional Progressive Pseudo Labeling (PPPL), a simple, yet effective technique that can be implemented in a few lines of code to build a more general domain adaptation technique that can be applied on several different input types. At the beginning of the training phase, PPPL progressively reduces target domain classification error, by training the model directly with pseudo-labeled target domain samples, while excluding samples with more likely wrong pseudo-labels from the training set and also postponing training on such samples. Experiments on 6 different datasets that include tasks such as anomaly detection, text sentiment analysis and image classification demonstrate that PPPL can beat other baselines and generalize better.



page 1

page 2

page 3

page 4


Asymmetric Tri-training for Unsupervised Domain Adaptation

Deep-layered models trained on a large number of labeled samples boost t...

Unsupervised Domain Adaptation via Structured Prediction Based Selective Pseudo-Labeling

Unsupervised domain adaptation aims to address the problem of classifyin...

Unsupervised Domain Adaptation with Progressive Adaptation of Subspaces

Unsupervised Domain Adaptation (UDA) aims to classify unlabeled target d...

A Fully Convolutional Tri-branch Network (FCTN) for Domain Adaptation

A domain adaptation method for urban scene segmentation is proposed in t...

Source-Free Progressive Graph Learning for Open-Set Domain Adaptation

Open-set domain adaptation (OSDA) has gained considerable attention in m...

Unsupervised Vehicle Re-identification with Progressive Adaptation

Vehicle re-identification (reID) aims at identifying vehicles across dif...

Domain-Adversarial Training of Neural Networks

We introduce a new representation learning approach for domain adaptatio...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.