Lifelong Ensemble Learning based on Multiple Representations for Few-Shot Object Recognition

TL;DR

This paper introduces a lifelong ensemble learning method using multiple representations, including deep features and handcrafted 3D shape descriptors, to improve open-ended, few-shot 3D object recognition for service robots.

Contribution

It proposes a novel lifelong ensemble learning framework with memory units for open-ended 3D object recognition, combining deep and handcrafted features, and demonstrates its effectiveness in real and simulated robot scenarios.

Findings

Ensemble learning improves lifelong few-shot recognition performance.

The approach outperforms state-of-the-art open-ended learning methods.

Significant benefits observed in lifelong learning scenarios.

Abstract

Service robots are integrating more and more into our daily lives to help us with various tasks. In such environments, robots frequently face new objects while working in the environment and need to learn them in an open-ended fashion. Furthermore, such robots must be able to recognize a wide range of object categories. In this paper, we present a lifelong ensemble learning approach based on multiple representations to address the few-shot object recognition problem. In particular, we form ensemble methods based on deep representations and handcrafted 3D shape descriptors. To facilitate lifelong learning, each approach is equipped with a memory unit for storing and retrieving object information instantly. The proposed model is suitable for open-ended learning scenarios where the number of 3D object categories is not fixed and can grow over time. We have performed extensive sets of experiments to assess the performance of the proposed approach in offline, and open-ended scenarios. For the evaluation purpose, in addition to real object datasets, we generate a large synthetic household objects dataset consisting of 27000 views of 90 objects. Experimental results demonstrate the effectiveness of the proposed method on online few-shot 3D object recognition tasks, as well as its superior performance over the state-of-the-art open-ended learning approaches. Furthermore, our results show that while ensemble learning is modestly beneficial in offline settings, it is significantly beneficial in lifelong few-shot learning situations. Additionally, we demonstrated the effectiveness of our approach in both simulated and real-robot settings, where the robot rapidly learned new categories from limited examples.