Search Results for author:
Found 11 papers, 8 papers with code
Linking vision and motion for self-supervised object-centric perception
Object-centric representations enable autonomous driving algorithms to reason about interactions between many independent agents and scene features.
Constellation: Learning relational abstractions over objects for compositional imagination
Learning structured representations of visual scenes is currently a major bottleneck to bridging perception with reasoning.
SIMONe: View-Invariant, Temporally-Abstracted Object Representations via Unsupervised Video Decomposition
Leveraging the shared structure that exists across different scenes, our model learns to infer two sets of latent representations from RGB video input alone: a set of "object" latents, corresponding to the time-invariant, object-level contents of the scene, as well as a set of "frame" latents, corresponding to global time-varying elements such as viewpoint.
Unsupervised Model Selection for Variational Disentangled Representation Learning
Disentangled representations have recently been shown to improve fairness, data efficiency and generalisation in simple supervised and reinforcement learning tasks.
COBRA: Data-Efficient Model-Based RL through Unsupervised Object Discovery and Curiosity-Driven Exploration
Data efficiency and robustness to task-irrelevant perturbations are long-standing challenges for deep reinforcement learning algorithms.
MONet: Unsupervised Scene Decomposition and Representation
The ability to decompose scenes in terms of abstract building blocks is crucial for general intelligence.
Spatial Broadcast Decoder: A Simple Architecture for Learning Disentangled Representations in VAEs
We present a simple neural rendering architecture that helps variational autoencoders (VAEs) learn disentangled representations.
Life-Long Disentangled Representation Learning with Cross-Domain Latent Homologies
Intelligent behaviour in the real-world requires the ability to acquire new knowledge from an ongoing sequence of experiences while preserving and reusing past knowledge.
Understanding disentangling in $β$-VAE
We present new intuitions and theoretical assessments of the emergence of disentangled representation in variational autoencoders.
DARLA: Improving Zero-Shot Transfer in Reinforcement Learning
Domain adaptation is an important open problem in deep reinforcement learning (RL).
SCAN: Learning Hierarchical Compositional Visual Concepts
SCAN learns concepts through fast symbol association, grounding them in disentangled visual primitives that are discovered in an unsupervised manner.
