AIConfPaper
← Search

Alexander Lerchner

12 accepted papers

2025

LayerLock: Non-collapsing Representation Learning with Progressive Freezing

Goker Erdogan, Nikhil Parthasarathy, Catalin Ionescu, Drew A. Hudson, Alexander Lerchner, Andrew Zisserman +2
ICCV 2025poster

We introduce LayerLock, a simple yet effective approach for self-supervised visual representation learning, that gradually transitions throughout training from predicting shallow features to deeper ones through progressive layer freezing. First, we make the observation that during training of video…

Cited by 0Source ↗PDF ↗Scholar ↗
2024

Leveraging VLM-Based Pipelines to Annotate 3D Objects

Rishabh Kabra, Loic Matthey, Alexander Lerchner, Niloy Mitra
ICML 2024poster

Pretrained vision language models (VLMs) present an opportunity to caption unlabeled 3D objects at scale. The leading approach to summarize VLM descriptions from different views of an object (Luo et al., 2023) relies on a language model (GPT4) to produce the final output. This text-based aggregation…

Cited by 6Source ↗PDF ↗Scholar ↗
2024

SODA: Bottleneck Diffusion Models for Representation Learning

Drew A. Hudson, Daniel Zoran, Mateusz Malinowski, Andrew K. Lampinen, Andrew Jaegle, James L. McClelland +3
CVPR 2024poster

We introduce SODA a self-supervised diffusion model designed for representation learning. The model incorporates an image encoder which distills a source view into a compact representation that in turn guides the generation of related novel views. We show that by imposing a tight bottleneck between…

Cited by 43Source ↗PDF ↗code ↗Scholar ↗
2021

Alchemy: A benchmark and analysis toolkit for meta-reinforcement learning agents

Jane X Wang, Michael King, Nicolas Pierre Mickael Porcel, Zeb Kurth-Nelson, Tina Zhu, Charlie Deck +11
NeurIPS 2021poster

There has been rapidly growing interest in meta-learning as a method for increasing the flexibility and sample efficiency of reinforcement learning. One problem in this area of research, however, has been a scarcity of adequate benchmark tasks. In general, the structure underlying past benchmarks ha…

Cited by 38Source ↗code ↗Scholar ↗
2021

PARTS: Unsupervised Segmentation With Slots, Attention and Independence Maximization

Daniel Zoran, Rishabh Kabra, Alexander Lerchner, Danilo J. Rezende
ICCV 2021poster

From an early age, humans perceive the visual world as composed of coherent objects with distinctive properties such as shape, size, and color. There is great interest in building models that are able to learn similar structure, ideally in an unsupervised manner. Learning such structure from complex…

Cited by 53PDF ↗Scholar ↗
2021

SIMONe: View-Invariant, Temporally-Abstracted Object Representations via Unsupervised Video Decomposition

Rishabh Kabra, Daniel Zoran, Goker Erdogan, Loic Matthey, Antonia Creswell, Matthew Botvinick +2
NeurIPS 2021poster

To help agents reason about scenes in terms of their building blocks, we wish to extract the compositional structure of any given scene (in particular, the configuration and characteristics of objects comprising the scene). This problem is especially difficult when scene structure needs to be inferr…

Cited by 82Source ↗PDF ↗Scholar ↗
2020

Unsupervised Model Selection for Variational Disentangled Representation Learning

Sunny Duan, Loic Matthey, Andre Saraiva, Nick Watters, Chris Burgess, Alexander Lerchner +1
ICLR 2020poster

Disentangled representations have recently been shown to improve fairness, data efficiency and generalisation in simple supervised and reinforcement learning tasks. To extend the benefits of disentangled representations to more complex domains and practical applications, it is important to enable hy…

Cited by 92Source ↗Scholar ↗
2019

Multi-Object Representation Learning with Iterative Variational Inference

Klaus Greff, Raphaël Lopez Kaufman, Rishabh Kabra, Nick Watters, Christopher Burgess, Daniel Zoran +3
ICML 2019oral

Human perception is structured around objects which form the basis for our higher-level cognition and impressive systematic generalization abilities. Yet most work on representation learning focuses on feature learning without even considering multiple objects, or treats segmentation as an (often su…

Cited by 565Source ↗PDF ↗code ↗Scholar ↗
2018

Life-Long Disentangled Representation Learning with Cross-Domain Latent Homologies

Alessandro Achille, Tom Eccles, Loic Matthey, Chris Burgess, Nicholas Watters, Alexander Lerchner +1
NeurIPS 2018spotlight

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. We propose a novel algorithm for unsupervised representation learning from piece-wise stationary visual data: Variational Autoenc…

Cited by 150Source ↗PDF ↗code ↗Scholar ↗
2018

SCAN: Learning Hierarchical Compositional Visual Concepts

Irina Higgins, Nicolas Sonnerat, Loic Matthey, Arka Pal, Christopher P Burgess, Matko Bošnjak +4
ICLR 2018poster

The seemingly infinite diversity of the natural world arises from a relatively small set of coherent rules, such as the laws of physics or chemistry. We conjecture that these rules give rise to regularities that can be discovered through primarily unsupervised experiences and represented as abstract…

Cited by 151Source ↗PDF ↗Scholar ↗
2017

DARLA: Improving Zero-Shot Transfer in Reinforcement Learning

Irina Higgins, Arka Pal, Andrei Rusu, Loic Matthey, Christopher Burgess, Alexander Pritzel +3
ICML 2017poster

Domain adaptation is an important open problem in deep reinforcement learning (RL). In many scenarios of interest data is hard to obtain, so agents may learn a source policy in a setting where data is readily available, with the hope that it generalises well to the target domain. We propose a new mu…

Cited by 560Source ↗PDF ↗Scholar ↗
2017

beta-VAE: Learning Basic Visual Concepts with a Constrained Variational Framework

Irina Higgins, Loic Matthey, Arka Pal, Christopher Burgess, Xavier Glorot, Matthew Botvinick +2
ICLR 2017poster

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 intelligence that is able to learn and reason in the same way that humans do. We introduce beta-VAE, a new state…

Cited by 6129Source ↗Scholar ↗