Adaptive Deep Learning through Visual Domain Localization

TL;DR

This paper introduces a localized deep domain adaptation method for robot vision that explicitly models and reduces local domain shifts, improving recognition across varied environments without needing all target classes during training.

Contribution

It proposes a novel end-to-end deep learning architecture that localizes domain shifts spatially, reducing parameters and enabling subset class training in robot vision applications.

Findings

Effective in reducing domain shift in robot vision scenarios.

Requires fewer parameters compared to traditional methods.

Demonstrates improved generalization on iCub World database.

Abstract

A commercial robot, trained by its manufacturer to recognize a predefined number and type of objects, might be used in many settings, that will in general differ in their illumination conditions, background, type and degree of clutter, and so on. Recent computer vision works tackle this generalization issue through domain adaptation methods, assuming as source the visual domain where the system is trained and as target the domain of deployment. All approaches assume to have access to images from all classes of the target during training, an unrealistic condition in robotics applications. We address this issue proposing an algorithm that takes into account the specific needs of robot vision. Our intuition is that the nature of the domain shift experienced mostly in robotics is local. We exploit this through the learning of maps that spatially ground the domain and quantify the degree of shift, embedded into an end-to-end deep domain adaptation architecture. By explicitly localizing the roots of the domain shift we significantly reduce the number of parameters of the architecture to tune, we gain the flexibility necessary to deal with subset of categories in the target domain at training time, and we provide a clear feedback on the rationale behind any classification decision, which can be exploited in human-robot interactions. Experiments on two different settings of the iCub World database confirm the suitability of our method for robot vision.