Program Generation from Diverse Video Demonstrations
This addresses the challenge of inductive reasoning for machines in computer vision, enabling program synthesis from diverse video inputs, though it appears incremental as it builds on prior works in this specific domain.
The paper tackles the problem of extracting general rules from multiple video demonstrations to generate programs, achieving state-of-the-art results with an 11.75% relative increase in program accuracy in the Vizdoom environment.
The ability to use inductive reasoning to extract general rules from multiple observations is a vital indicator of intelligence. As humans, we use this ability to not only interpret the world around us, but also to predict the outcomes of the various interactions we experience. Generalising over multiple observations is a task that has historically presented difficulties for machines to grasp, especially when requiring computer vision. In this paper, we propose a model that can extract general rules from video demonstrations by simultaneously performing summarisation and translation. Our approach differs from prior works by framing the problem as a multi-sequence-to-sequence task, wherein summarisation is learnt by the model. This allows our model to utilise edge cases that would otherwise be suppressed or discarded by traditional summarisation techniques. Additionally, we show that our approach can handle noisy specifications without the need for additional filtering methods. We evaluate our model by synthesising programs from video demonstrations in the Vizdoom environment achieving state-of-the-art results with a relative increase of 11.75% program accuracy on prior works