Reusable Slotwise Mechanisms

TL;DR

Re-usable slotwise mechanisms (RSM) improve object dynamics modeling by enabling dynamic, modular, and context-aware interactions among object slots, leading to better generalization and performance in scene understanding tasks.

Contribution

This work introduces RSM, a novel framework that uses communication among object slots and a central contextual information mechanism for dynamic, reusable interaction modeling.

Findings

RSM outperforms state-of-the-art methods in future prediction tasks.

RSM demonstrates superior performance in downstream tasks like VQA and action planning.

RSM exhibits strong out-of-distribution generalization capabilities.

Abstract

Agents with the ability to comprehend and reason about the dynamics of objects would be expected to exhibit improved robustness and generalization in novel scenarios. However, achieving this capability necessitates not only an effective scene representation but also an understanding of the mechanisms governing interactions among object subsets. Recent studies have made significant progress in representing scenes using object slots. In this work, we introduce Reusable Slotwise Mechanisms, or RSM, a framework that models object dynamics by leveraging communication among slots along with a modular architecture capable of dynamically selecting reusable mechanisms for predicting the future states of each object slot. Crucially, RSM leverages the Central Contextual Information (CCI), enabling selected mechanisms to access the remaining slots through a bottleneck, effectively allowing for modeling of higher order and complex interactions that might require a sparse subset of objects. Experimental results demonstrate the superior performance of RSM compared to state-of-the-art methods across various future prediction and related downstream tasks, including Visual Question Answering and action planning. Furthermore, we showcase RSM's Out-of-Distribution generalization ability to handle scenes in intricate scenarios.