AIConfPaper
← Search

Catalin Ionescu

9 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

Learning from One Continuous Video Stream

João Carreira, Michael King, Viorica Patraucean, Dilara Gokay, Catalin Ionescu, Yi Yang +6
CVPR 2024poster

We introduce a framework for online learning from a single continuous video stream - the way people and animals learn without mini-batches data augmentation or shuffling. This poses great challenges given the high correlation between consecutive video frames and there is very little prior work on it…

Cited by 3Source ↗PDF ↗Scholar ↗
2022

Perceiver IO: A General Architecture for Structured Inputs & Outputs

Andrew Jaegle, Sebastian Borgeaud, Jean-Baptiste Alayrac, Carl Doersch, Catalin Ionescu, David Ding +9
ICLR 2022spotlight

A central goal of machine learning is the development of systems that can solve many problems in as many data domains as possible. Current architectures, however, cannot be applied beyond a small set of stereotyped settings, as they bake in domain & task assumptions or scale poorly to large inputs o…

Cited by 698Source ↗PDF ↗code ↗Scholar ↗
2020

Making Sense of Reinforcement Learning and Probabilistic Inference

Brendan O'Donoghue, Ian Osband, Catalin Ionescu
ICLR 2020spotlight

Reinforcement learning (RL) combines a control problem with statistical estimation: The system dynamics are not known to the agent, but can be learned through experience. A recent line of research casts ‘RL as inference’ and suggests a particular framework to generalize the RL problem as probabilist…

Cited by 52Source ↗Scholar ↗
2019

Unsupervised Control Through Non-Parametric Discriminative Rewards

David Warde-Farley, Tom Van de Wiele, Tejas Kulkarni, Catalin Ionescu, Steven Hansen, Volodymyr Mnih
ICLR 2019poster

Learning to control an environment without hand-crafted rewards or expert data remains challenging and is at the frontier of reinforcement learning research. We present an unsupervised learning algorithm to train agents to achieve perceptually-specified goals using only a stream of observations and…

Cited by 201Source ↗PDF ↗Scholar ↗
2019

Unsupervised Learning of Object Keypoints for Perception and Control

Tejas D Kulkarni, Ankush Gupta, Catalin Ionescu, Sebastian Borgeaud, Malcolm Reynolds, Andrew Zisserman +1
NeurIPS 2019poster

The study of object representations in computer vision has primarily focused on developing representations that are useful for image classification, object detection, or semantic segmentation as downstream tasks. In this work we aim to learn object representations that are useful for control and rei…

Cited by 235Source ↗PDF ↗code ↗Scholar ↗
2016

Using Fast Weights to Attend to the Recent Past

Jimmy Ba, Geoffrey E. Hinton, Volodymyr Mnih, Joel Z. Leibo, Catalin Ionescu
NeurIPS 2016oral

Until recently, research on artificial neural networks was largely restricted to systems with only two types of variable: Neural activities that represent the current or recent input and weights that learn to capture regularities among inputs, outputs and payoffs. There is no good reason for this re…

Cited by 317Source ↗PDF ↗Scholar ↗