Abstract
AbstractIn real-world object recognition, there are numerous object classes to be recognized. Traditional image recognition methods based on supervised learning can only recognize object classes present in the training data, and have limited applicability in the real world. In contrast, humans can recognize novel objects by questioning and acquiring knowledge about them. Inspired by this, we propose a framework for acquiring external knowledge by generating questions that enable the model to instantly recognize novel objects. Our framework comprises three components: the object classifier (OC), which performs knowledge-based object recognition, the question generator (QG), which generates knowledge-aware questions to acquire novel knowledge, and the policy decision (PD) Model, which determines the “policy” of questions to be asked. The PD model utilizes two strategies, namely “confirmation” and “exploration”—the former confirms candidate knowledge while the latter explores completely new knowledge. Our experiments demonstrate that the proposed pipeline effectively acquires knowledge about novel objects compared to several baselines, and realizes novel object recognition utilizing the obtained knowledge. We also performed a real-world evaluation in which humans responded to the generated questions, and the model used the acquired knowledge to retrain the OC, which is a fundamental step toward a real-world human-in-the-loop learning-by-asking framework. We plan to release the dataset immediately upon acceptance of our work.
Funder
Moonshot Research and Development Program
Core Research for Evolutional Science and Technology
Institute for AI and Beyond of the University of Tokyo
Publisher
Springer Science and Business Media LLC
Subject
Artificial Intelligence,Computer Vision and Pattern Recognition,Software