Calum Heggan

Calum Heggan

PhD Candidate @ University Of Edinburgh & partnered with Thales UK. Interested in Few-Shot learning and Anomaly Detection for sequential signals

Sitemap

A list of all the posts and pages found on the site. For you robots out there is an XML version available for digesting as well.

Pages

Posts

MT-SLVR: Co-Learning Towards Harmony in Audio Processing

22 minute read

Published:

‘MT-SLVR: Multi-Task Self-Supervised Learning for Transformation In(Variant) Representations’ was released in late May 2023, after being accepted to InterSpeech23. It proposed a novel multi-task learning approach, capable of co-learning seemingly conflicting features. This blog aims to be a more informal and digestible breakdown of the work. All relevant code, or links to, can be found here.

MetaAudio: A Benchmark Breakdown

20 minute read

Published:

‘MetaAudio: A Few-Shot Classification Benchmark’ was released in early April. It contains a variety of benchmark results for researchers to beat in the future. This blog aims to be a more easily digestible breakdown of the work. All of the code for MetaAudio can be found here

portfolio

publications

MetaAudio: A Few-Shot Audio Classification Benchmark

Published in ICANN22, 2022

This paper establishes a novel few-shot audio classification benchmark

Recommended citation: Heggan, C., Budgett, S., Hospedales, T., Yaghoobi, M. (2022). MetaAudio: A Few-Shot Audio Classification Benchmark. In: Pimenidis, E., Angelov, P., Jayne, C., Papaleonidas, A., Aydin, M. (eds) Artificial Neural Networks and Machine Learning – ICANN 2022. ICANN 2022. Lecture Notes in Computer Science, vol 13529. Springer, Cham. https://doi.org/10.1007/978-3-031-15919-0_19

talks

Improving Generalisation of Meta-learning for Sequential Data Anomaly Detection

Published:

Abstract Meta-learning, or learning to learn, has proven to be a popular framework in dealing with few shot problems in recent times. Most of the work using this family of techniques focuses on the image domain, leaving many other interesting data modalities and settings largely unexplored. This project looks at expanding this scope of the available research by considering both time series data and the task of anomaly detection. In the first year of the PhD, work has largely been devoted to time series, focusing specifically on few-shot acoustic classification and its standardisation within literature.

What is Meta-Learning? An Introduction to the Setting and Algorithms

Published:

Abstract To date, the majority of the breakthroughs seen in machine learning have been in domains or settings where there was an abundance of data, either real or simulated. In contrast, the capability for humans to quickly recognise and discriminate between types of phenomena, for example in visual or acoustic settings, remains unmatched. Meta-learning, or learning to learn, has proven to be a popular and successful framework in dealing with these kind of few-shot problems. In this presentation I will give some general context to how these frameworks are created and used as well as some details on the different algorithms that have been a staple of the field.

MetaAudio: A Few-Shot Audio Classification Benchmark

Published:

Abstract Currently available benchmarks for few-shot learning (machine learning with few training examples) are limited in the domains they cover, primarily focusing on image classification. This work aims to alleviate this reliance on image-based benchmarks by offering the first comprehensive, public and fully reproducible audio based alternative, covering a variety of sound domains and experimental settings. We compare the few-shot classification performance of a variety of techniques on seven audio datasets (spanning environmental sounds to human-speech). Extending this, we carry out in-depth analyses of joint training (where all datasets are used during training) and cross-dataset adaptation protocols, establishing the possibility of a generalised audio few-shot classification algorithm. Our experimentation shows gradient-based meta-learning methods such as MAML and Meta-Curvature consistently outperform both metric and baseline methods. We also demonstrate that the joint training routine helps overall generalisation for the environmental sound databases included, as well as being a somewhat-effective method of tackling the cross-dataset/domain setting.

teaching

Private Tuition

Private, Online & In-person, 2019

Private tuition for both primary and secondary students. For primary students I taught both math and science, this also included the preparation of lesson plans and content. For secondary students I tutored both National 5 and Higher mathematics.

Intro to Computer Vision Marking

Undergraduate course, University of Edinburgh, Informatics, 2021

Aided in the marking of the 2021 Intro to Computer Vision (IVC) course. Used the Gradescope technology.

Personal Development for Engineering Tutor and Demonstrator

Undergraduate course, University of Edinburgh, Engineering, 2022

My primary tutoring responsibilities included hosting seminars and tutorials, starting discussions around professional and ethical values in Engineering. Two pieces of written coursework (essay style) were also mandatory for students to complete over the duration of the course. I was involved in the marking of both of these pieces of work.