research
∙
05/24/2023
Semantic Segmentation by Semantic Proportions
Semantic segmentation is a critical task in computer vision that aims to...
share
research
∙
02/15/2022
Generalisation and the Risk–Entropy Curve
In this paper we show that the expected generalisation performance of a ...
research
∙
02/14/2022
Orthogonalising gradients to speed up neural network optimisation
The optimisation of neural networks can be sped up by orthogonalising th...
research
∙
11/22/2021
On Data-centric Myths
The community lacks theory-informed guidelines for building good data se...
research
∙
10/26/2021
On the Effects of Data Distortion on Model Analysis and Training
Data modification can introduce artificial information. It is often assu...
research
∙
08/13/2021
GeoCLR: Georeference Contrastive Learning for Efficient Seafloor Image Interpretation
This paper describes Georeference Contrastive Learning of visual Represe...
research
∙
07/26/2021
Language Models as Zero-shot Visual Semantic Learners
Visual Semantic Embedding (VSE) models, which map images into a rich sem...
research
∙
07/26/2021
What Remains of Visual Semantic Embeddings
Zero shot learning (ZSL) has seen a surge in interest over the decade fo...
research
∙
05/02/2021
Object detection for crabs in top-view seabed imagery
This report presents the application of object detection on a database o...
research
∙
05/01/2021
RotLSTM: Rotating Memories in Recurrent Neural Networks
Long Short-Term Memory (LSTM) units have the ability to memorise and use...
research
∙
08/18/2020
Linear Disentangled Representations and Unsupervised Action Estimation
Disentangled representation learning has seen a surge in interest over r...
research
∙
02/27/2020
Understanding and Enhancing Mixed Sample Data Augmentation
Mixed Sample Data Augmentation (MSDA) has received increasing attention ...
research
∙
11/11/2019
Rethinking Generalisation
In this paper, we present a new approach to computing the generalisation...
research
∙
06/15/2019
Deep Set Prediction Networks
We study the problem of predicting a set from a feature vector with a de...
research
∙
06/13/2019
A Variational Autoencoder for Probabilistic Non-Negative Matrix Factorisation
We introduce and demonstrate the variational autoencoder (VAE) for proba...
research
∙
06/06/2019
FSPool: Learning Set Representations with Featurewise Sort Pooling
We introduce a pooling method for sets of feature vectors based on sorti...
research
∙
02/05/2019
Minimum description length as an objective function for non-negative matrix factorization
Non-negative matrix factorization (NMF) is a dimensionality reduction te...
research
∙
12/10/2018
Learning Representations of Sets through Optimized Permutations
Representations of sets are challenging to learn because operations on s...
research
∙
02/15/2018