research
∙
05/24/2023
On progressive sharpening, flat minima and generalisation
We present a new approach to understanding the relationship between loss...
share
research
∙
10/19/2022
Hierarchical classification at multiple operating points
Many classification problems consider classes that form a hierarchy. Cla...
research
∙
10/10/2022
A global analysis of global optimisation
Theoretical understanding of the training of deep neural networks has ma...
research
∙
02/04/2022
Learning with Neighbor Consistency for Noisy Labels
Recent advances in deep learning have relied on large, labelled datasets...
research
∙
04/06/2021
Local Metrics for Multi-Object Tracking
This paper introduces temporally local metrics for Multi-Object Tracking...
research
∙
03/26/2018
Long-term Tracking in the Wild: A Benchmark
We introduce a new video dataset and benchmark to assess single-object t...
research
∙
02/20/2018
Devon: Deformable Volume Network for Learning Optical Flow
We propose a lightweight neural network model, Deformable Volume Network...
research
∙
06/30/2016
Fully-Convolutional Siamese Networks for Object Tracking
The problem of arbitrary object tracking has traditionally been tackled ...
research
∙
06/16/2016
Learning feed-forward one-shot learners
One-shot learning is usually tackled by using generative models or discr...
research
∙
12/04/2015