Low-shot Object Learning with Mutual Exclusivity Bias
Abstract
This paper introduces Low-shot Object Learning with Mutual Exclusivity Bias (LSME), the first computational framing of mutual exclusivity bias, a phenomenon commonly observed in infants during word learning. We provide a novel dataset, comprehensive baselines, and a state-of-the-art method to enable the ML community to tackle this challenging learning task. The goal of LSME is to analyze an RGB image of a scene containing multiple objects and correctly associate a previously-unknown object instance with a provided category label. This association is then used to perform low-shot learning to test category generalization. We provide a data generation pipeline for the LSME problem and conduct a thorough analysis of the factors that contribute to its difficulty. Additionally, we evaluate the performance of multiple baselines, including state-of-the-art foundation models. Finally, we present a baseline approach that outperforms state-of-the-art models in terms of low-shot accuracy.
Cite
@article{arxiv.2312.03533,
title = {Low-shot Object Learning with Mutual Exclusivity Bias},
author = {Anh Thai and Ahmad Humayun and Stefan Stojanov and Zixuan Huang and Bikram Boote and James M. Rehg},
journal= {arXiv preprint arXiv:2312.03533},
year = {2023}
}
Comments
Accepted at NeurIPS 2023, Datasets and Benchmarks Track. Project website https://ngailapdi.github.io/projects/lsme/