Semantic segmentation is a critical task in computer vision that aims to...
In this paper we show that the expected generalisation performance of a
...
The optimisation of neural networks can be sped up by orthogonalising th...
The community lacks theory-informed guidelines for building good data se...
Data modification can introduce artificial information. It is often assu...
This paper describes Georeference Contrastive Learning of visual
Represe...
Visual Semantic Embedding (VSE) models, which map images into a rich sem...
Zero shot learning (ZSL) has seen a surge in interest over the decade fo...
This report presents the application of object detection on a database o...
Long Short-Term Memory (LSTM) units have the ability to memorise and use...
Disentangled representation learning has seen a surge in interest over r...
Mixed Sample Data Augmentation (MSDA) has received increasing attention ...
In this paper, we present a new approach to computing the generalisation...
We study the problem of predicting a set from a feature vector with a de...
We introduce and demonstrate the variational autoencoder (VAE) for
proba...
We introduce a pooling method for sets of feature vectors based on sorti...
Non-negative matrix factorization (NMF) is a dimensionality reduction
te...
Representations of sets are challenging to learn because operations on s...
Visual Question Answering (VQA) models have struggled with counting obje...