TY - JOUR
T1 - Low-shot Object Learning with Mutual Exclusivity Bias
AU - Thai, Anh
AU - Humayun, Ahmad
AU - Stojanov, Stefan
AU - Huang, Zixuan
AU - Boote, Bikram
AU - Rehg, James M.
N1 - Publisher Copyright:
© 2023 Neural information processing systems foundation. All rights reserved.
PY - 2023
Y1 - 2023
N2 - 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. Code and data are available at https://github.com/rehglab/LSME.
AB - 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. Code and data are available at https://github.com/rehglab/LSME.
UR - http://www.scopus.com/inward/record.url?scp=85191176348&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85191176348&partnerID=8YFLogxK
M3 - Conference article
AN - SCOPUS:85191176348
SN - 1049-5258
VL - 36
JO - Advances in Neural Information Processing Systems
JF - Advances in Neural Information Processing Systems
T2 - 37th Conference on Neural Information Processing Systems, NeurIPS 2023
Y2 - 10 December 2023 through 16 December 2023
ER -