AlignNet: Unsupervised Entity Alignment
arXiv:2007.08973
Abstract
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.
References in corpus (8)
- MONet: Unsupervised Scene Decomposition and Representation
- Neural Map: Structured Memory for Deep Reinforcement Learning
- Reasoning About Physical Interactions with Object-Oriented Prediction and Planning
- Human Instruction-Following with Deep Reinforcement Learning via Transfer-Learning from Text
- AutoShuffleNet: Learning Permutation Matrices via an Exact Lipschitz Continuous Penalty in Deep Convolutional Neural Networks
- Occlusion resistant learning of intuitive physics from videos
- Probing Emergent Semantics in Predictive Agents via Question Answering
- Learning Visual Dynamics Models of Rigid Objects using Relational Inductive Biases