My name is Oisin Mac Aodha (how to pronounce my name) and I am a Reader (aka Associate Professor) in Machine Learning in the School of Informatics at the University of Edinburgh (UoE). I was a Turing Fellow from 2021 to 2024, currently am an ELLIS Scholar, and a founder of the Turing interest group on biodiversity monitoring and forecasting. My current research interests are in the areas of computer vision and machine learning, with an specific emphasis on 3D understanding, human-in-the-loop methods, and AI for conservation and biodiversity monitoring.
From 2016-2019 I was fortunate to be a postdoc in Prof. Pietro Perona'sComputational Vision Lab at Caltech working with the Visipedia team.
Previous to Caltech, I spent three great years (2013-2016) as a postdoc in the Department of Computer Science at University College London (UCL) with Prof. Gabriel Brostow and Prof. Kate Jones. There I worked on interactive machine learning, where our goal was to design algorithms to enable non-programming scientists to semi-automatically explore events of interest in vast quantities of audio and visual data.
I did both my MSc (with Dr. Simon Prince) and PhD (with Prof. Gabriel Brostow) at UCL and have an undergraduate degree in electronic engineering from the University of Galway in Ireland. Before my PhD, I was a research assistant for one year in Prof. Marc Pollefeys' group at ETH Zurich.
Oct 2023: I'll be an Area Chair for CVPR 2024 and ECCV 2024.
Sep 2023: You can read about our collaboration with iNaturalist on improving computer vision here and here.
Sep 2023: I'll be speaking at the Frontiers of Monocular 3D Perception workshop at ICCV 2023.
Jul 2023: I'll be speaking at the 26th BMVA Computer Vision Summer School.
Jun 2023: I'll be speaking at the 2nd Monocular Depth Estimation Challenge Workshop at CVPR 2023 on June 18th.
May 2023: I'll be speaking at the Leveraging AI to Quantify Biodiversity and Ecosystem Change Workshop on May 18th.
Jan 2023: Co-organising FGVC10 workshop at CVPR 2023.
Jan 2023: I'll be an Area Chair for ICML 2023 and ICCV 2023.
Jan 2023: I'll be speaking at the Monocular Depth Estimation Challenge Workshop on January 7th.
Dec 2022: I'll be speaking at the Workshop on Challenges of Fine-Grained Image Analysis on December 5th.
Nov 2022: We have just launched our Turing Interest Group on Biodiversity Monitoring and Forecasting.
Oct 2022: I'll be an Area Chair for CVPR 2023.
Jun 2022: I'll be speaking at the 25th BMVA Computer Vision Summer School in July and the CV4Ecology Summer School in August.
Apr 2022: I'll be an Area Chair for NeurIPS 2022.
Mar 2022: Open postdoc position in AI for biodiversity monitoring at the University of Edinburgh. More info here.
Feb 2022: I'll be an Area Chair for ECCV 2022.
Jan 2022: Co-organising FGVC9 workshop at CVPR 2022.
Dec 2021: Open postdoc in position human-in-the-loop AI at the University of Edinburgh. More info here.
Sep 2021: Selected as a Turing Fellow and ELLIS Scholar.
May 2021: I'll be an Area Chair for BMVC 2021.
Mar 2021: FGVC8 will be held on June 25th 2021. More info here.
Mar 2021: I'll be an Area Chair for NeurIPS 2021.
Dec 2020: Co-organising FGVC8 workshop at CVPR 2021.
Sep 2020: I'll be an Area Chair for ICLR 2021.
Aug 2020: I'll be a Senior Program Committee Member for AAAI 2021.
Jul 2020: Presenting at the AI for Social Good workshop. Video of the talk is here.
Jul 2020: Giving a talk at the Optimizing Human Learning workshop. Video of the talk is here.
Jun 2020: You can find the videos of the talks from our FGVC7 workshop here.
May 2020: I'll be an Area Chair for NeurIPS 2020.
Mar 2020: Serving as a Program Chair for BMVC 2020. Consider submitting!
Dec 2019: Co-organising FGVC7 workshop at CVPR 2020.
Nov 2019: Vacancies: Several openings for PhD students - see here for more details.
Oct 2019: Just started as a Lecturer (aka Assistant Professor) in Machine Learning at the University of Edinburgh.
Jul 2019: Serving on the Program Committee for Workshop on Computer Vision for Wildlife Conservation at ICCV 2019. Consider submitting your papers!
Jun 2019: Serving as an Area Chair for WACV 2020.
May 2019: Code released for our Monodepth2 paper.
Apr 2019: FGVC6 competitions now live on Kaggle.
Jan 2019: Co-organising FGVC6 workshop at CVPR 2019.
Sep 2018: Serving as an Area Chair for ACCV 2018.
Jul 2018: Check out Niantic's occlusion demo using our monocular depth work.
Jun 2018: FGVC5 held at CVPR 2018.
Feb 2018: Launched iNaturalist 2018 challenge.
Jan 2018: Gave a talk to LA school children about the importance of bats.
Jan 2018: Co-organising FGVC5 workshop at CVPR 2018.
Aug 2017: Read about the iNaturalist Challenge 2017
that we ran in conjunction with Caltech, iNaturalist, Cornell, Google, and Kaggle.
Jul 2017: Helped organize the Fourth Fine-Grained Visual Categorization workshop at CPVR this summer.
Jul 2017: Read about our monocular depth estimation project at
UCL and
The Engineer.
Jun 2017: Live deployment of our bat detection system in the former Olympic Park in London.
Read about it on the BBC or follow our twitter page to get
daily updates.
Sep 2016: Interviewed by SVT for our work on using machine learning to detect bats.
Aug 2016: Read about our handwriting synthesis project at the BBC,
UCL,
Engadget,
Reuters,
Gizmodo,
and The Irish Times.
Jul 2016: Moved to Caltech to do a postdoc.
Mar 2016: Gave a talk about Bat Detective at UCL's Grant Museum.
Apr 2015: Blog about bat call detection over at Methods in Ecology and Evolution.
INQUIRE: A Natural World Text-to-Image Retrieval Benchmark
Edward Vendrow, Omiros Pantazis, Alexander Shepard, Gabriel Brostow, Kate E. Jones, Oisin Mac Aodha, Sara Beery, and Grant Van Horn
NeurIPS 2024 Datasets and Benchmarks Track [paper][webpage]
Combining Observational Data and Language for Species Range Estimation
Max Hamilton, Christian Lange, Elijah Cole, Alexander Shepard, Samuel Heinrich, Oisin Mac Aodha, Grant Van Horn, and Subhransu Maji
NeurIPS 2024 [paper][code]
Labeled Data Selection for Category Discovery
Bingchen Zhao, Nico Lang, Serge Belongie, and Oisin Mac Aodha
ECCV 2024 [paper]
Generating Binary Species Range Maps
Filip Dorm, Chris Lange, Scott Loarie, and Oisin Mac Aodha
Workshop on Computer Vision for Ecology at ECCV 2024 [paper][code]
Deep Learning-Based Ecological Analysis of Camera Trap Images is Impacted by Training Data Quality and Size
Omiros Pantazis, Peggy Bevan, Holly Pringle, Guilherme Braga Ferreira, Daniel J. Ingram, Emily Madsen, Liam Thomas, Dol Raj Thanet, Thakur Silwal, Santosh Rayamajhi, Gabriel Brostow, Oisin Mac Aodha, and Kate Jones
arXiv 2024 [paper]
Click to Grasp: Zero-Shot Precise Manipulation via Visual Diffusion Descriptors
Nikolaos Tsagkas, Jack Rome, Subramanian Ramamoorthy, Oisin Mac Aodha, and Chris Xiaoxuan Lu
IROS 2024 [paper][webpage]
Vision Learners Meet Web Image-Text Pairs
Bingchen Zhao, Quan Cui, Hao Wu, Osamu Yoshie, Cheng Yang, and Oisin Mac Aodha
TMLR 2024 [paper][webpage]
Less is More: Discovering Concise Network Explanations
Neehar Kondapaneni, Markus Marks, Oisin Mac Aodha, and Pietro Perona
ICLR 2024 Workshop on Representational Alignment (Re-Align) [paper][webpage][code]
Self-Supervised Multimodal Learning: A Survey
Yongshuo Zong, Oisin Mac Aodha, and Timothy Hospedales
PAMI 2024 [paper][webpage]
Enhancing 2D Representation Learning with a 3D Prior
Mehmet Aygün, Prithviraj Dhar, Zhicheng Yan, Oisin Mac Aodha, and Rakesh Ranjan
CVPR 2024 Workshop on Representation Learning with Very Limited Images [paper]
GeoGen: Geometry-Aware Generative Modeling via Signed Distance Functions
Salvatore Esposito, Qingshan Xu, Kacper Kania, Charlie Hewitt, Octave Mariotti, Lohit Petikam, Julien Valentin, Arno Onken, and Oisin Mac Aodha
CVPR 2024 Workshop on Generative Models for Computer Vision [paper][webpage]
SAOR: Single-View Articulated Object Reconstruction
Mehmet Aygün and Oisin Mac Aodha
CVPR 2024 [paper][webpage]
Improving Semantic Correspondence with Viewpoint-Guided Spherical Maps
Octave Mariotti, Oisin Mac Aodha, and Hakan Bilen
CVPR 2024 (Oral) [paper][webpage]
AirPlanes: Accurate Plane Estimation via 3D-Consistent Embeddings
Jamie Watson, Filippo Aleotti, Mohamed Sayed, Zawar Qureshi, Oisin Mac Aodha, Gabriel Brostow, Michael Firman, and Sara Vicente
CVPR 2024 [paper][webpage]
From Coarse to Fine-Grained Open-Set Recognition
Nico Lang, Vésteinn Snæbjarnarson, Elijah Cole, Oisin Mac Aodha, Christian Igel, and Serge Belongie
CVPR 2024 [paper][webpage]
Whombat: An Open-Source Annotation Tool for Machine Learning Development in Bioacoustics
Santiago Martinez Balvanera, Oisin Mac Aodha, Matthew Weldy, Holly Pringle, Ella Browning, and Kate Jones
arXiv 2023 [paper][code]
Active Learning-Based Species Range Estimation
Christian Lange, Elijah Cole, Grant Van Horn, and Oisin Mac Aodha
NeurIPS 2023 [paper][code]
Incremental Generalized Category Discovery
Bingchen Zhao and Oisin Mac Aodha
ICCV 2023 [paper][code][webpage]
Spatial Implicit Neural Representations for Global-Scale Species Mapping
Elijah Cole, Grant Van Horn, Christian Lange, Alexander Shepard, Patrick Leary, Pietro Perona, Scott Loarie, and Oisin Mac Aodha
ICML 2023 [paper][code]
VL-Fields: Towards Language-Grounded Neural Implicit Spatial Representations
Nikolaos Tsagkas, Oisin Mac Aodha, and Chris Xiaoxuan Lu
Representations, Abstractions, and Priors for Robot Learning Workshop at ICRA 2023 [paper][webpage]
Virtual Occlusions Through Implicit Depth
Jamie Watson, Mohamed Sayed, Zawar Qureshi, Gabriel Brostow, Sara Vicente, Oisin Mac Aodha, and Michael Firman
CVPR 2023 [paper][code][webpage][video]
Heightfields for Efficient Scene Reconstruction for AR
Jamie Watson, Sara Vicente, Oisin Mac Aodha, Clement Godard, Gabriel Brostow, and Michael Firman
WACV 2023 [paper][webpage]
Towards a General Approach for Bat Echolocation Detection and Classification
Oisin Mac Aodha, Santiago Martínez Balvanera, Elise Damstra, Martyn Cooke, Philip Eichinski, Ella Browning, Michel Barataud, Katherine Boughey, Roger Coles, Giada Giacomini, M. Cristina Mac Swiney G., Martin K. Obrist, Stuart Parsons, Thomas Sattler, and Kate Jones
bioRxiv 2022 [paper][code][demo]
SVL-Adapter: Self-Supervised Adapter for Vision-Language Pretrained Models
Omiros Pantazis, Gabriel Brostow, Kate Jones, and Oisin Mac Aodha
BMVC 2022 [paper][code][video]
ViewNeRF: Unsupervised Viewpoint Estimation Using Category-Level Neural Radiance Fields
Octave Mariotti, Oisin Mac Aodha, and Hakan Bilen
BMVC 2022 [paper][code]
An Action Is Worth Multiple Words: Handling Ambiguity in Action Recognition
Kiyoon Kim, Davide Moltisanti, Oisin Mac Aodha, and Laura Sevilla-Lara
BMVC 2022 [paper][code]
Capturing Temporal Information in a Single Frame: Channel Sampling Strategies for Action Recognition
Kiyoon Kim, Shreyank Gowda, Oisin Mac Aodha, and Laura Sevilla-Lara
BMVC 2022 [paper][code]
Demystifying Unsupervised Semantic Correspondence Estimation
Mehmet Aygün and Oisin Mac Aodha
ECCV 2022 [paper][webpage][code]
Visual Knowledge Tracing
Neehar Kondapaneni, Pietro Perona, and Oisin Mac Aodha
ECCV 2022 [paper][code/data]
On Label Granularity and Object Localization
Elijah Cole, Kimberly Wilber, Grant Van Horn, Xuan Yang, Marco Fornoni, Pietro Perona, Serge Belongie, Andrew Howard, and
Oisin Mac Aodha
ECCV 2022 [paper][code/data]
Exploring Fine-grained Audiovisual Categorization with the SSW60 Dataset
Grant Van Horn*, Rui Qian*, Kimberly Wilber, Hartwig Adam, Oisin Mac Aodha, and Serge Belongie
ECCV 2022 [paper][code/data]
When Does Contrastive Visual Representation Learning Work?
Elijah Cole, Xuan Yang, Kimberly Wilber, Oisin Mac Aodha, and Serge Belongie
CVPR 2022 [paper][webpage][video]
Fine-Grained Image Analysis with Deep Learning: A Survey
Xiu-Shen Wei, Yi-Zhe Song, Oisin Mac Aodha, Jianxin Wu, Yuxin Peng, Jinhui Tang, Jian Yang, and Serge Belongie
PAMI 2021 [paper]
Shazam for Bats: Internet of Things for Continuous Real-Time Biodiversity Monitoring
Sarah Gallacher, Duncan Wilson, Alison Fairbrass, Daniyar Turmukhambetov, Michael Firman, Stefan Kreitmayer, Oisin Mac Aodha, Gabriel Brostow, and Kate Jones
IET Smart Cities 2021 [paper]
Focus on the Positives: Self-Supervised Learning for Biodiversity Monitoring
Omiros Pantazis, Gabriel Brostow, Kate Jones, and Oisin Mac Aodha
ICCV 2021 [paper][code][video]
ViewNet: Unsupervised Viewpoint Estimation from Conditional Generation
Octave Mariotti, Oisin Mac Aodha, and Hakan Bilen
ICCV 2021 [paper][code]
Benchmarking Representation Learning for Natural World Image Collections
Grant Van Horn, Elijah Cole, Sara Beery, Kimberly Wilber, Serge Belongie, and Oisin Mac Aodha
CVPR 2021 (Oral) [paper][code/data][video]
Multi-Label Learning From Single Positive Labels
Elijah Cole, Oisin Mac Aodha, Titouan Lorieul, Pietro Perona, Dan Morris, and Nebojsa Jojic
CVPR 2021 [paper][video][code]
The Temporal Opportunist: Self-Supervised Multi-Frame Monocular Depth
Jamie Watson, Oisin Mac Aodha, Victor Prisacariu, Gabriel Brostow, and Michael Firman
CVPR 2021 [paper][code]
Learning Stereo from Single Images
Jamie Watson, Oisin Mac Aodha, Daniyar Turmukhambetov, Gabriel Brostow, and Michael Firman
ECCV 2020 (Oral) [paper][code]
Geocoding of Trees From Street Addresses and Street-Level Images
Daniel Laumer, Nico Lang, Natalie van Doorn, Oisin Mac Aodha, Pietro Perona, and Jan Dirk Wegner
Journal of Photogrammetry and Remote Sensing 2020 [paper][arxiv]
Teaching Multiple Concepts to a Forgetful Learner
Anette Hunziker, Yuxin Chen, Oisin Mac Aodha, Manuel Gomez Rodriguez, Andreas Krause, Pietro Perona, Yisong Yue, and Adish Singla
NeurIPS 2019 [paper]
Presence-Only Geographical Priors for Fine-Grained Image Classification
Oisin Mac Aodha, Elijah Cole, and Pietro Perona
ICCV 2019 [paper][code][video][webpage]
Digging Into Self-Supervised Monocular Depth Estimation
Clement Godard, Oisin Mac Aodha, Michael Firman, and Gabriel Brostow
ICCV 2019 [paper][video][code]
Understanding the Role of Adaptivity in Machine Teaching: The Case of Version Space Learners
Yuxin Chen, Adish Singla, Oisin Mac Aodha, Pietro Perona, and Yisong Yue
NeurIPS 2018 [paper]
It's all Relative: Monocular 3D Human Pose Estimation from Weakly Supervised Data
Matteo Ruggero Ronchi, Oisin Mac Aodha, Robert Eng, and Pietro Perona
BMVC 2018 (Oral) [paper][webpage][code][video]
Teaching Categories to Human Learners with Visual Explanations
Oisin Mac Aodha, Shihan Su, Yuxin Chen, Pietro Perona, and Yisong Yue
CVPR 2018 (Spotlight) [paper][code][video]
Context Embedding Networks
Kun ho Kim, Oisin Mac Aodha, and Pietro Perona
CVPR 2018 (Spotlight) [paper]
The iNaturalist Species Classification and Detection Dataset
Grant Van Horn, Oisin Mac Aodha, Yang Song, Yin Cui, Chen Sun, Alex Shepard, Hartwig Adam, Pietro Perona, and Serge Belongie
CVPR 2018 (Spotlight) [paper][webpage][video]
Bat Detective - Deep Learning Tools for Bat Acoustic Signal Detection
Oisin Mac Aodha, Rory Gibb, Kate Barlow, Ella Browning, Michael Firman, Robin Freeman, Briana Harder, Libby Kinsey, Gary Mead, Stuart Newson, Ivan Pandourski, Stuart Parsons, Jon Russ, Abigel Szodoray-Paradi, Farkas Szodoray-Paradi, Elena Tilova, Mark Girolami, Gabriel J. Brostow, and Kate E. Jones
PLOS Computational Biology 2018
[paper][code][webpage]
Near-Optimal Machine Teaching via Explanatory Teaching Sets
Yuxin Chen, Oisin Mac Aodha, Shihan Su, Pietro Perona, and Yisong Yue
AISTATS 2018 [paper]
Interpretable Machine Teaching via Feature Feedback
Shihan Su, Yuxin Chen, Oisin Mac Aodha, Pietro Perona, and Yisong Yue
NeurIPS Workshop Teaching Machines, Robots, and Humans 2017 [paper]
Unsupervised Monocular Depth Estimation with Left-Right Consistency
Clement Godard, Oisin Mac Aodha, and Gabriel J. Brostow
CVPR 2017 (Oral) [paper][code][webpage]
Structured Prediction of Unobserved Voxels From a Single Depth Image
Michael Firman, Oisin Mac Aodha, Simon Julier, and Gabriel J. Brostow
CVPR 2016 (Oral) [paper][webpage]
My text in Your Handwriting
Tom S.F. Haines, Oisin Mac Aodha, and Gabriel J. Brostow
Transactions on Graphics (SIGGRAPH) 2016 [paper][code][webpage]
Becoming the Expert - Interactive Multi-Class Machine Teaching
Edward Johns, Oisin Mac Aodha, and Gabriel J. Brostow
CVPR 2015 (Oral) [paper][webpage]
Putting the Scientist in the Loop - Accelerating Scientific Progress with Interactive Machine Learning
Oisin Mac Aodha, Vassilios Stathopoulos, Michael Terry, Kate E. Jones, Gabriel J. Brostow, and Mark Girolami
ICPR 2014 [paper]
Hierarchical Subquery Evaluation for Active Learning on a Graph
Oisin Mac Aodha, Neill D.F. Campbell, Jan Kautz, and Gabriel J. Brostow
CVPR 2014 (Oral) [paper][webpage]
Revisiting Example Dependent Cost-Sensitive Learning with Decision Trees
Oisin Mac Aodha and Gabriel J. Brostow
ICCV 2013 [paper][webpage]
Learning a Confidence Measure for Optical Flow
Oisin Mac Aodha, Ahmad Humayun, Marc Pollefeys, and Gabriel J. Brostow
PAMI 2013 [paper][webpage]
Patch Based Synthesis for Single Depth Image Super-Resolution
Oisin Mac Aodha, Neill D.F. Campbell, Arun Nair, and Gabriel J. Brostow
ECCV 2012 [paper][webpage]
Learning to Find Occlusion Regions
Ahmad Humayun, Oisin Mac Aodha, and Gabriel J. Brostow
CVPR 2011 [paper][webpage]
Segmenting Video Into Classes of Algorithm-Suitability
Oisin Mac Aodha, Gabriel J Brostow, and Marc Pollefeys
CVPR 2010 [paper][webpage]
Evolving Plastic Responses in Artificial Cell Models
John Maher, Fearghal Morgan, and Oisin Mac Aodha
Congress on Evolutionary Computation 2009 [paper]