Robust Place Categorization with Deep Domain Generalization

by   Massimiliano Mancini, et al.

Traditional place categorization approaches in robot vision assume that training and test images have similar visual appearance. Therefore, any seasonal, illumination and environmental changes typically lead to severe degradation in performance. To cope with this problem, recent works have proposed to adopt domain adaptation techniques. While effective, these methods assume that some prior information about the scenario where the robot will operate is available at training time. Unfortunately, in many cases this assumption does not hold, as we often do not know where a robot will be deployed. To overcome this issue, in this paper we present an approach which aims at learning classification models able to generalize to unseen scenarios. Specifically, we propose a novel deep learning framework for domain generalization. Our method develops from the intuition that, given a set of different classification models associated to known domains (e.g. corresponding to multiple environments, robots), the best model for a new sample in the novel domain can be computed directly at test time by optimally combining the known models. To implement our idea, we exploit recent advances in deep domain adaptation and design a Convolutional Neural Network architecture with novel layers performing a weighted version of Batch Normalization. Our experiments, conducted on three common datasets for robot place categorization, confirm the validity of our contribution.


page 2

page 8


Adaptive Deep Learning through Visual Domain Localization

A commercial robot, trained by its manufacturer to recognize a predefine...

A Brief Review of Domain Adaptation

Classical machine learning assumes that the training and test sets come ...

A Domain Agnostic Normalization Layer for Unsupervised Adversarial Domain Adaptation

We propose a normalization layer for unsupervised domain adaption in sem...

AdaGraph: Unifying Predictive and Continuous Domain Adaptation through Graphs

The ability to categorize is a cornerstone of visual intelligence, and a...

AdaGraph: Unifying Predictive and ContinuousDomain Adaptation through Graphs

The ability to categorize is a cornerstone of visual intelligence, and a...

Batch Normalization Embeddings for Deep Domain Generalization

Domain generalization aims at training machine learning models to perfor...

Learning Deep Visual Object Models From Noisy Web Data: How to Make it Work

Deep networks thrive when trained on large scale data collections. This ...

Please sign up or login with your details

Forgot password? Click here to reset