NEOL: Toward Never-Ending Object Learning for robots

Learning to recognize objects based on names is a crucial capability for personal robots. Recent recognition methods successfully learn to recognize objects in a train-once-then-test setting. Yet, these methods do not apply readily to robotic settings, where a robot might continuously encounter new objects and new names. In this work, we present a framework for Never-Ending Object Learning (NEOL). Our framework automatically learns to organize object names into a semantic hierarchy using crowdsourcing and background knowledge bases. It then uses the hierarchy to improve the consistency and efficiency of annotating objects. It also adapts information from additional image datasets to learn object classifiers from a very small number of training examples. We present experiments to test the performance of the adaptation method and demonstrate the full system in a never-ending object learning experiment.

Authors

• Yuyin Sun
• Dieter Fox

Keywords

• Robots
• Crowdsourcing
• Training
• Semantics
• Sun
• Object recognition
• Training data
• Additional Imaging
• Training Examples
• Object Naming
• Training Set
• Convolutional Neural Network
• RGB Images
• Baseline Methods
• Target Domain
• Leaf Node
• Number Of Assignments
• Domain Adaptation
• Source Domain
• Maximum A Posteriori
• Training Instances
• Image Annotation
• Domain Adaptation Methods
• Label Propagation
• Set Of Names
• Unseen Objects
• Target Domain Images
• Target Domain Data
• ImageNet Data
• Domain Experts
• Positive Training
• Robotic Applications