NOD-CC: A Hybrid CBR-CNN Architecture for Novel Object Discovery
Loading...
Author/Creator
Author/Creator ORCID
Date
2019-08-09
Type of Work
Department
Program
Citation of Original Publication
Turner, JT; Floyd, Michael W.; Gupta, Kalyan; Oates, Tim; NOD-CC: A Hybrid CBR-CNN Architecture for Novel Object Discovery; Case-Based Reasoning Research and Development. ICCBR 2019. Lecture Notes in Computer Science, vol 11680. Springer, Cham; https://doi.org/10.1007/978-3-030-29249-2_25
Rights
This item is likely protected under Title 17 of the U.S. Copyright Law. Unless on a Creative Commons license, for uses protected by Copyright Law, contact the copyright holder or the author.
Abstract
Deep Learning methods have shown a rapid increase in popularity due to their state-of-the-art performance on many machine learning tasks. However, these methods often rely on extremely large datasets to accurately train the underlying machine learning models. For supervised learning techniques, the human effort required to acquire, encode, and label a sufficiently large dataset may add such a high cost that deploying the algorithms is infeasible. Even if a sufficient workforce exists to create such a dataset, the human annotators may differ in the quality, consistency, and level of granularity of their labels. Any impact this has on the overall dataset quality will ultimately impact the potential performance of an algorithm trained on it. This paper partially addresses this issue by providing an approach, called NOD-CC, for discovering novel object types in images using a combination of Convolutional Neural Networks (CNNs) and Case-Based Reasoning (CBR). The CNN component labels instances of known object types while deferring to the CBR component to identify and label novel, or poorly understood, object types. Thus, our approach leverages the state-of-the-art performance of CNNs in situations where sufficient high-quality training data exists, while minimizing its limitations in data-poor situations. We empirically evaluate our approach on a popular computer vision dataset and show significant improvements to objects classification performance when full knowledge of potential class labels is not known in advance.