no code implementations • CVPR 2021 • Olivia Wiles, Sebastien Ehrhardt, Andrew Zisserman
We propose a new approach to determine correspondences between image pairs in the wild under large changes in illumination, viewpoint, context, and material.
1 code implementation • NeurIPS 2020 • Sebastien Ehrhardt, Oliver Groth, Aron Monszpart, Martin Engelcke, Ingmar Posner, Niloy Mitra, Andrea Vedaldi
We present RELATE, a model that learns to generate physically plausible scenes and videos of multiple interacting objects.
1 code implementation • 17 Jun 2020 • Sylvestre-Alvise Rebuffi, Sebastien Ehrhardt, Kai Han, Andrea Vedaldi, Andrew Zisserman
We present LSD-C, a novel method to identify clusters in an unlabeled dataset.
1 code implementation • ICLR 2020 • Kai Han, Sylvestre-Alvise Rebuffi, Sebastien Ehrhardt, Andrea Vedaldi, Andrew Zisserman
In this work we address this problem by combining three ideas: (1) we suggest that the common approach of bootstrapping an image representation using the labeled data only introduces an unwanted bias, and that this can be avoided by using self-supervised learning to train the representation from scratch on the union of labelled and unlabelled data; (2) we use rank statistics to transfer the model's knowledge of the labelled classes to the problem of clustering the unlabelled images; and, (3) we train the data representation by optimizing a joint objective function on the labelled and unlabelled subsets of the data, improving both the supervised classification of the labelled data, and the clustering of the unlabelled data.
1 code implementation • 21 May 2019 • Sylvestre-Alvise Rebuffi, Sebastien Ehrhardt, Kai Han, Andrea Vedaldi, Andrew Zisserman
The first is a simple but effective one: we leverage the power of transfer learning among different tasks and self-supervision to initialize a good representation of the data without making use of any label.
no code implementations • 1 Apr 2019 • Samuel Albanie, James Thewlis, Sebastien Ehrhardt, Joao Henriques
The theory of deep learning is now considered largely solved, and is well understood by researchers and influencers alike.
6 code implementations • ICLR 2019 • João F. Henriques, Sebastien Ehrhardt, Samuel Albanie, Andrea Vedaldi
Instead, we propose to keep a single estimate of the gradient projected by the inverse Hessian matrix, and update it once per iteration.
1 code implementation • 21 May 2018 • João F. Henriques, Sebastien Ehrhardt, Samuel Albanie, Andrea Vedaldi
We propose a fast second-order method that can be used as a drop-in replacementfor current deep learning solvers.
no code implementations • 14 May 2018 • Sebastien Ehrhardt, Aron Monszpart, Niloy Mitra, Andrea Vedaldi
While learning models of intuitive physics is an increasingly active area of research, current approaches still fall short of natural intelligences in one important regard: they require external supervision, such as explicit access to physical states, at training and sometimes even at test times.
no code implementations • 22 Dec 2017 • Sebastien Ehrhardt, Aron Monszpart, Niloy Mitra, Andrea Vedaldi
In order to be able to leverage the approximation capabilities of artificial intelligence techniques in such physics related contexts, researchers have handcrafted the relevant states, and then used neural networks to learn the state transitions using simulation runs as training data.
no code implementations • 1 Mar 2017 • Sebastien Ehrhardt, Aron Monszpart, Niloy J. Mitra, Andrea Vedaldi
Evolution has resulted in highly developed abilities in many natural intelligences to quickly and accurately predict mechanical phenomena.