Publications

A Survey of Self-Supervised and Few-Shot Object Detection
Gabriel Huang
Issam Hadj Laradji
David Vazquez
Simon Lacoste-Julien
Pau Rodriguez
Labeling data is often expensive and time-consuming, especially for tasks such as object detection and instance segmentation, which require … (see more)dense labeling of the image. While few-shot object detection is about training a model on novel (unseen) object classes with little data, it still requires prior training on many labeled examples of base (seen) classes. On the other hand, self-supervised methods aim at learning representations from unlabeled data which transfer well to downstream tasks such as object detection. Combining few-shot and self-supervised object detection is a promising research direction. In this survey, we review and characterize the most recent approaches on few-shot and self-supervised object detection. Then, we give our main takeaways and discuss future research directions. Project page: https://gabrielhuang.github.io/fsod-survey/.
2023-04-01
IEEE Transactions on Pattern Analysis and Machine Intelligence (published)
doi.org
arxiv.org
Visual Question Answering From Another Perspective: CLEVR Mental Rotation Tests
Christopher Beckham
Martin Weiss
Florian Golemo
Sina Honari
Derek Nowrouzezahrai
Chris Pal
2023-04-01
Pattern Recognition (published)
doi.org
openreview.net
Bayesian stroke modeling details sex biases in the white matter substrates of aphasia
Julius M Kernbach
Gesa Hartwigsen
Jae‐Sung Lim
Hee-Joon Bae
Kyung‐Ho Yu
Gottfried Schlaug
Anna K. Bonkhoff
Natalia S. Rost
Danilo Bzdok
2023-03-31
Communications Biology (published)
doi.org
MLGCN: An Ultra Efficient Graph Convolution Neural Model For 3D Point Cloud Analysis
Mohammad Khodadad
Morteza Rezanejad
Ali Shiraee Kasmaee
Kaleem Siddiqi
Dirk Bernhardt-Walther
Hamidreza Mahyar
2023-03-31
ArXiv (preprint)
doi.org
arxiv.org
Varepsilon kú mask: Integrating Yorùbá cultural greetings into machine translation
Idris Akinade
Jesujoba Oluwadara Alabi
David Ifeoluwa Adelani
Clement Odoje
Dietrich Klakow
This paper investigates the performance of massively multilingual neural machine translation (NMT) systems in translating Yorùbá greetings… (see more) (kú mask), which are a big part of Yorùbá language and culture, into English. To evaluate these models, we present IkiniYorùbá, a Yorùbá-English translation dataset containing some Yorùbá greetings, and sample use cases. We analysed the performance of different multilingual NMT systems including Google and NLLB and show that these models struggle to accurately translate Yorùbá greetings into English. In addition, we trained a Yorùbá-English model by fine-tuning an existing NMT model on the training split of IkiniYorùbá and this achieved better performance when compared to the pre-trained multilingual NMT models, although they were trained on a large volume of data.
2023-03-31
ArXiv (preprint)
doi.org
arxiv.org
Behavioural equivalences for continuous-time Markov processes
Linan Chen
Florence Clerc
Prakash Panangaden
2023-03-30
Mathematical Structures in Computer Science (published)
doi.org
Machine learning application development: practitioners’ insights
Md Saidur Rahman
Foutse Khomh
Alaleh Hamidi
Jinghui Cheng
Giuliano Antoniol
Hironori Washizaki
2023-03-30
Software Quality Journal (published)
doi.org
arxiv.org
Cross-sectional and longitudinal neuroanatomical profiles of distinct clinical (adaptive) outcomes in autism
Charlotte M. Pretzsch
Dorothea L. Floris
Tim Schäfer
Anke Bletsch
Caroline Gurr
Michael V. Lombardo
Chris H. Chatham
Julian Tillmann
Tony Charman
Martina Arenella
Emily J. H. Jones
Sara Ambrosino
Thomas Bourgeron
Guillaume Dumas
Freddy Cliquet
Claire Leblond
Eva Loth
Beth Oakley
Jan K. Buitelaar
Simon Baron-Cohen … (see 7 more)
Christian Beckmann
Antonio Persico
Tobias Banaschewski
Sarah Durston
Christine M. Freitag
Declan Murphy
Christine Ecker
2023-03-29
Molecular Psychiatry (published)
doi.org
FMAS: Fast Multi-Objective SuperNet Architecture Search for Semantic Segmentation
Zhuoran Xiong
Marihan Amein
O. Therrien
Warren Gross
Brett Meyer
2023-03-29
ArXiv (preprint)
doi.org
arxiv.org
A Halfspace-Mass Depth-Based Method for Adversarial Attack Detection
Marine Picot
Federica Granese
Guillaume Staerman
Marco Romanelli
Francisco Messina
Pablo Piantanida
Pierre Colombo
2023-03-28
TMLR (accepted)
openreview.net
openreview.net
Multi-view manifold learning of human brain state trajectories
Erica Lindsey Busch
Je-chun Huang
Andrew Benz
Tom Wallenstein
Guillaume Lajoie
Guy Wolf
Smita Krishnaswamy
Nicholas Turk-Browne
2023-03-27
Nature Computational Science (published)
doi.org
Green Federated Learning
Ashkan Yousefpour
Sheng Guo
Ashish V. Shenoy
Sayan Ghosh
Pierre Stock
Kiwan Maeng
Schalk-Willem Kruger
Michael Rabbat
Carole-Jean Wu
Ilya Mironov
The rapid progress of AI is fueled by increasingly large and computationally intensive machine learning models and datasets. As a consequenc… (see more)e, the amount of compute used in training state-of-the-art models is exponentially increasing (doubling every 10 months between 2015 and 2022), resulting in a large carbon footprint. Federated Learning (FL) - a collaborative machine learning technique for training a centralized model using data of decentralized entities - can also be resource-intensive and have a significant carbon footprint, particularly when deployed at scale. Unlike centralized AI that can reliably tap into renewables at strategically placed data centers, cross-device FL may leverage as many as hundreds of millions of globally distributed end-user devices with diverse energy sources. Green AI is a novel and important research area where carbon footprint is regarded as an evaluation criterion for AI, alongside accuracy, convergence speed, and other metrics. In this paper, we propose the concept of Green FL, which involves optimizing FL parameters and making design choices to minimize carbon emissions consistent with competitive performance and training time. The contributions of this work are two-fold. First, we adopt a data-driven approach to quantify the carbon emissions of FL by directly measuring real-world at-scale FL tasks running on millions of phones. Second, we present challenges, guidelines, and lessons learned from studying the trade-off between energy efficiency, performance, and time-to-train in a production FL system. Our findings offer valuable insights into how FL can reduce its carbon footprint, and they provide a foundation for future research in the area of Green AI.
2023-03-26
ArXiv (preprint)
doi.org
arxiv.org