Understanding Visual Concepts with Continuation Learning

2016/02/22 by WILLIAM F. WHITNEY, Michael Chang, Whitney, William F. +5 · 6 citations
Computer Science · #Advanced Vision and Imaging #FOS: Computer and information sciences #Face and Expression Recognition #Generative Adversarial Networks and Image Synthesis #Machine Learning (cs.LG)

paper · pdf · doi:10.48550/arxiv.1602.06822

openalex publication_date 2016/02/22 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

We introduce a neural network architecture and a learning algorithm to produce factorized symbolic representations. We propose to learn these concepts by observing consecutive frames, letting all the components of the hidden representation except a small discrete set (gating units) be predicted from the previous frame, and let the factors of variation in the next frame be represented entirely by these discrete gated units (corresponding to symbolic representations). We demonstrate the efficacy of our approach on datasets of faces undergoing 3D transformations and Atari 2600 games.

Cited by

• Hierarchical Deep Reinforcement Learning: Integrating Temporal Abstraction and Intrinsic Motivation
• Unsupervised Learning of Object Keypoints for Perception and Control
• Early Visual Concept Learning with Unsupervised Deep Learning
• Are Disentangled Representations Helpful for Abstract Visual Reasoning?
• Odd-One-Out Representation Learning
• Disentangling Video with Independent Prediction

Related

• Look-Ahead Selective Plasticity for Continual Learning of Visual Tasks
• Extracting Symbolic Sequences from Visual Representations via Self-Supervised Learning
• Representation Learning by Learning to Count
• SCAN: Learning Hierarchical Compositional Visual Concepts
• Continual Neural Mapping: Learning An Implicit Scene Representation from Sequential Observations