• Publications
  • Influence
beta-VAE: Learning Basic Visual Concepts with a Constrained Variational Framework
Learning an interpretable factorised representation of the independent data generative factors of the world without supervision is an important precursor for the development of artificial
Understanding disentangling in β-VAE
TLDR
A modification to the training regime of β-VAE is proposed, that progressively increases the information capacity of the latent code during training, to facilitate the robust learning of disentangled representations in β- VAE, without the previous trade-off in reconstruction accuracy.
Multi-Object Representation Learning with Iterative Variational Inference
TLDR
This work argues for the importance of learning to segment and represent objects jointly, and demonstrates that, starting from the simple assumption that a scene is composed of multiple entities, it is possible to learn to segment images into interpretable objects with disentangled representations.
DARLA: Improving Zero-Shot Transfer in Reinforcement Learning
TLDR
A new multi-stage RL agent, DARLA (DisentAngled Representation Learning Agent), which learns to see before learning to act, which significantly outperforms conventional baselines in zero-shot domain adaptation scenarios.
MONet: Unsupervised Scene Decomposition and Representation
TLDR
The Multi-Object Network (MONet) is developed, which is capable of learning to decompose and represent challenging 3D scenes into semantically meaningful components, such as objects and background elements.
Understanding disentangling in $\beta$-VAE
TLDR
A modification to the training regime of $\ beta$-VAE is proposed, that progressively increases the information capacity of the latent code during training, to facilitate the robust learning of disentangled representations in $\beta$- VAE, without the previous trade-off in reconstruction accuracy.
Towards a Definition of Disentangled Representations
TLDR
It is suggested that those transformations that change only some properties of the underlying world state, while leaving all other properties invariant are what gives exploitable structure to any kind of data.
Early Visual Concept Learning with Unsupervised Deep Learning
TLDR
An unsupervised approach for learning disentangled representations of the underlying factors of variation by applying the same learning pressures as have been suggested to act in the ventral visual stream in the brain is proposed.
Life-Long Disentangled Representation Learning with Cross-Domain Latent Homologies
TLDR
This work proposes a novel algorithm for unsupervised representation learning from piece-wise stationary visual data: Variational Autoencoder with Shared Embeddings (VASE), which automatically detects shifts in the data distribution and allocates spare representational capacity to new knowledge, while simultaneously protecting previously learnt representations from catastrophic forgetting.
SCAN: Learning Abstract Hierarchical Compositional Visual Concepts
TLDR
SCAN (Symbol-Concept Association Network), a new framework for learning concepts in the visual domain capable of multimodal bi-directional inference and traversal and manipulation of the implicit hierarchy of compositional visual concepts through symbolic instructions and learnt logical recombination operations, is described.
...
...