Beyond Object Recognition: A New Benchmark towards Object Concept Learning
This work addresses the challenge of object concept learning for embodied AI, though it is incremental as it builds on existing object recognition methods.
The authors tackled the problem of machines learning higher-level object knowledge beyond recognition by proposing the Object Concept Learning (OCL) task, which requires reasoning about object affordances and attributes, and they built a densely annotated knowledge base and a baseline model (OCRN) that effectively infers object knowledge while following causal relations.
Understanding objects is a central building block of artificial intelligence, especially for embodied AI. Even though object recognition excels with deep learning, current machines still struggle to learn higher-level knowledge, e.g., what attributes an object has, and what can we do with an object. In this work, we propose a challenging Object Concept Learning (OCL) task to push the envelope of object understanding. It requires machines to reason out object affordances and simultaneously give the reason: what attributes make an object possesses these affordances. To support OCL, we build a densely annotated knowledge base including extensive labels for three levels of object concept (category, attribute, affordance), and the causal relations of three levels. By analyzing the causal structure of OCL, we present a baseline, Object Concept Reasoning Network (OCRN). It leverages causal intervention and concept instantiation to infer the three levels following their causal relations. In experiments, OCRN effectively infers the object knowledge while following the causalities well. Our data and code are available at https://mvig-rhos.com/ocl.