Skip to yearly menu bar Skip to main content


Low-shot Object Learning with Mutual Exclusivity Bias

Anh Thai · Ahmad Humayun · Stefan Stojanov · Zixuan Huang · Bikram Boote · James Rehg

Great Hall & Hall B1+B2 (level 1) #2026
[ ]
[ Paper [ Poster [ OpenReview
Wed 13 Dec 8:45 a.m. PST — 10:45 a.m. PST


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 SOTA 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

Chat is not available.