AlignNet: Unsupervised Entity Alignment
This addresses a key bottleneck for agents using object-based inputs in AI, though it appears incremental as it builds on existing segmentation models.
The paper tackles the problem of aligning segmented objects across time-steps in unsupervised scene segmentation, presenting AlignNet as a solution to enable downstream use of object representations.
Recently developed deep learning models are able to learn to segment scenes into component objects without supervision. This opens many new and exciting avenues of research, allowing agents to take objects (or entities) as inputs, rather that pixels. Unfortunately, while these models provide excellent segmentation of a single frame, they do not keep track of how objects segmented at one time-step correspond (or align) to those at a later time-step. The alignment (or correspondence) problem has impeded progress towards using object representations in downstream tasks. In this paper we take steps towards solving the alignment problem, presenting the AlignNet, an unsupervised alignment module.