activity
20192021
collaborators

5 papers

cs.LG2021

How Sensitive are Meta-Learners to Dataset Imbalance?

Mateusz Ochal, Massimiliano Patacchiola, Amos Storkey +2

Meta-Learning (ML) has proven to be a useful tool for training Few-Shot Learning (FSL) algorithms by exposure to batches of tasks sampled from a meta-dataset. However, the standard…

cs.CV2020

Similarity-based data mining for online domain adaptation of a sonar ATR system

Jean de Bodinat, Thomas Guerneve, Jose Vazquez +1

Due to the expensive nature of field data gathering, the lack of training data often limits the performance of Automatic Target Recognition (ATR) systems. This problem is often add…

cs.CV2020

A Comparison of Few-Shot Learning Methods for Underwater Optical and Sonar Image Classification

Mateusz Ochal, Jose Vazquez, Yvan Petillot +1

Deep convolutional neural networks generally perform well in underwater object recognition tasks on both optical and sonar images. Many such methods require hundreds, if not thousa…

eess.IV2020

Unlimited Resolution Image Generation with R2D2-GANs

Marija Jegorova, Antti Ilari Karjalainen, Jose Vazquez +1

In this paper we present a novel simulation technique for generating high quality images of any predefined resolution. This method can be used to synthesize sonar scans of size equ…

cs.LG2019

Full-Scale Continuous Synthetic Sonar Data Generation with Markov Conditional Generative Adversarial Networks

Marija Jegorova, Antti Ilari Karjalainen, Jose Vazquez +1

Deployment and operation of autonomous underwater vehicles is expensive and time-consuming. High-quality realistic sonar data simulation could be of benefit to multiple application…