Flexible deep transfer learning by separate feature embeddings and manifold alignment

by   Samuel Rivera, et al.

Object recognition is a key enabler across industry and defense. As technology changes, algorithms must keep pace with new requirements and data. New modalities and higher resolution sensors should allow for increased algorithm robustness. Unfortunately, algorithms trained on existing labeled datasets do not directly generalize to new data because the data distributions do not match. Transfer learning (TL) or domain adaptation (DA) methods have established the groundwork for transferring knowledge from existing labeled source data to new unlabeled target datasets. However, current DA approaches assume similar source and target feature spaces and suffer in the case of massive domain shifts or changes in the feature space. Existing methods assume the data are either the same modality, or can be aligned to a common feature space. Therefore, most methods are not designed to support a fundamental domain change such as visual to auditory data. We propose a novel deep learning framework that overcomes this limitation by learning separate feature extractions for each domain while minimizing the distance between the domains in a latent lower-dimensional space. The alignment is achieved by considering the data manifold along with an adversarial training procedure. We demonstrate the effectiveness of the approach versus traditional methods with several ablation experiments on synthetic, measured, and satellite image datasets. We also provide practical guidelines for training the network while overcoming vanishing gradients which inhibit learning in some adversarial training settings.


page 1

page 2

page 3

page 4


Filtered Manifold Alignment

Domain adaptation is an essential task in transfer learning to leverage ...

A Survey of Unsupervised Domain Adaptation for Visual Recognition

While huge volumes of unlabeled data are generated and made available in...

Multi-source Domain Adaptation in the Deep Learning Era: A Systematic Survey

In many practical applications, it is often difficult and expensive to o...

Adversarial Knowledge Transfer from Unlabeled Data

While machine learning approaches to visual recognition offer great prom...

Seeking Similarities over Differences: Similarity-based Domain Alignment for Adaptive Object Detection

In order to robustly deploy object detectors across a wide range of scen...

Domain Adaptation by Topology Regularization

Deep learning has become the leading approach to assisted target recogni...

Domain Adaptation with Randomized Expectation Maximization

Domain adaptation (DA) is the task of classifying an unlabeled dataset (...

Please sign up or login with your details

Forgot password? Click here to reset