X-VoE: Measuring eXplanatory Violation of Expectation in Physical Events
This work addresses the problem of enabling AI to understand physical events like humans, which is incremental as it builds on existing paradigms but introduces a new benchmark and learning approach.
The paper tackles the challenge of replicating human intuitive physics in AI by introducing X-VoE, a benchmark dataset based on the Violation of Expectation paradigm, and presents a model that aligns with human commonsense and reconstructs concealed scenes from visual sequences.
Intuitive physics is pivotal for human understanding of the physical world, enabling prediction and interpretation of events even in infancy. Nonetheless, replicating this level of intuitive physics in artificial intelligence (AI) remains a formidable challenge. This study introduces X-VoE, a comprehensive benchmark dataset, to assess AI agents' grasp of intuitive physics. Built on the developmental psychology-rooted Violation of Expectation (VoE) paradigm, X-VoE establishes a higher bar for the explanatory capacities of intuitive physics models. Each VoE scenario within X-VoE encompasses three distinct settings, probing models' comprehension of events and their underlying explanations. Beyond model evaluation, we present an explanation-based learning system that captures physics dynamics and infers occluded object states solely from visual sequences, without explicit occlusion labels. Experimental outcomes highlight our model's alignment with human commonsense when tested against X-VoE. A remarkable feature is our model's ability to visually expound VoE events by reconstructing concealed scenes. Concluding, we discuss the findings' implications and outline future research directions. Through X-VoE, we catalyze the advancement of AI endowed with human-like intuitive physics capabilities.