Multi-Instance Active Learning with Online Labeling for Object Recognition

摘要

Robots deployed in domains characterized by non-deterministic action outcomes and unforeseen changes frequently need considerable knowledge about the do-main and tasks they have to perform. Humans, however, may not have the time and expertise to provide elaborate or accurate domain knowledge, and it may be difficult for robots to obtain many labeled training samples of domain objects and events. For widespread deployment, robots thus need the ability to incrementally and auto-matically extract relevant domain knowledge from mul-timodal sensor inputs, acquiring and using human feed-back when such feedback is necessary and available. This paper describes a multiple-instance active learning algorithm for such incremental learning in the context of building models of relevant domain objects. We in-troduce the concept of bag uncertainty, enabling robots to identify the need for feedback, and to incrementally revise learned object models by associating visual cues extracted from images with verbal cues extracted from limited high-level human feedback. Images of indoor and outdoor scenes drawn from the IAPR TC-12 bench-mark dataset are used to show that our algorithm pro-vides better object recognition accuracy than a state of the art multiple-instance active learning algorithm. 1