Publications

Kubric: A scalable dataset generator
Klaus Greff
Francois Belletti
Lucas Beyer
Carl Doersch
Yilun Du
Daniel Duckworth
David J. Fleet
Dan Gnanapragasam
Florian Golemo
Charles Herrmann
Thomas N. Kipf
Abhijit Kundu
Dmitry Lagun
Issam Hadj Laradji
Hsueh-Ti Liu
H. Meyer
Yishu Miao
Derek Nowrouzezahrai
Cengiz Oztireli
Etienne Pot … (voir 14 de plus)
Noha Radwan
Daniel Rebain
Sara Sabour
Mehdi S. M. Sajjadi
Matan Sela
Vincent Sitzmann
Austin Stone
Deqing Sun
Suhani Vora
Ziyu Wang
Tianhao Wu
Kwang Moo Yi
Fangcheng Zhong
Andrea Tagliasacchi
Data is the driving force of machine learning, with the amount and quality of training data often being more important for the performance o… (voir plus)f a system than architecture and training details. But collecting, processing and annotating real data at scale is difficult, expensive, and frequently raises additional privacy, fairness and legal concerns. Synthetic data is a powerful tool with the potential to address these shortcomings: 1) it is cheap 2) supports rich ground-truth annotations 3) offers full control over data and 4) can circumvent or mitigate problems regarding bias, privacy and licensing. Unfortunately, software tools for effective data generation are less mature than those for architecture design and training, which leads to fragmented generation efforts. To address these problems we introduce Kubric, an open-source Python framework that interfaces with PyBullet and Blender to generate photo-realistic scenes, with rich annotations, and seamlessly scales to large jobs distributed over thousands of machines, and generating TBs of data. We demonstrate the effectiveness of Kubric by presenting a series of 13 different generated datasets for tasks ranging from studying 3D NeRF models to optical flow estimation. We release Kubric, the used assets, all of the generation code, as well as the rendered datasets for reuse and modification.
2022-03-07
ArXiv (preprint)
doi.org
arxiv.org
Misinterpreting the horseshoe effect in neuroscience
Timothée Proix
Matt Perich
Tomislav Milekovic
2022-03-07
bioRxiv (prépublication)
doi.org
Monocular Robot Navigation with Self-Supervised Pretrained Vision Transformers
Miguel Saavedra-Ruiz
Sacha Morin
Liam Paull
In this work, we consider the problem of learning a perception model for monocular robot navigation using few annotated images. Using a Visi… (voir plus)on Transformer (ViT) pretrained with a label-free self-supervised method, we successfully train a coarse image segmentation model for the Duckietown environment using 70 training images. Our model performs coarse image segmentation at the
2022-03-07
ArXiv (preprint)
doi.org
arxiv.org
Cross-ethnicity/race generalization failure of behavioral prediction from resting-state functional connectivity
Jingwei Li
Danilo Bzdok
Jianzhong Chen
Angela Tam
Leon Qi
Rong Ooi
Avram J. Holmes
Tian Ge
K. Patil
M. Jabbi
Simon B. Eickhoff
B.T. Thomas Yeo
Sarah Genon
Algorithmic biases that favor majority populations pose a key challenge to the application of machine learning for precision medicine. Here,… (voir plus) we assessed such bias in prediction models of behavioral phenotypes from brain functional magnetic resonance imaging. We examined the prediction bias using two independent datasets (preadolescent versus adult) of mixed ethnic/racial composition. When predictive models were trained on data dominated by white Americans (WA), out-of-sample prediction errors were generally higher for African Americans (AA) than for WA. This bias toward WA corresponds to more WA-like brain-behavior association patterns learned by the models. When models were trained on AA only, compared to training only on WA or an equal number of AA and WA participants, AA prediction accuracy improved but stayed below that for WA. Overall, the results point to the need for caution and further research regarding the application of current brain-behavior prediction models in minority populations.
2022-03-01
Science Advances (published)
doi.org
Multistep networks for roll force prediction in hot strip rolling mill
Shuh-Rong Shen
Denzel Guye
Xiaoping Ma
S. Yue
Narges Armanfard
2022-03-01
Machine Learning with Applications (published)
doi.org
Software-Engineering Design Patterns for Machine Learning Applications
Hironori Washizaki
Foutse Khomh
Yann‐Gaël Guéhéneuc
Hironori Takeuchi
Naotake Natori
Takuo Doi
Satoshi Okuda
In this study, a multivocal literature review identified 15 software-engineering design patterns for machine learning applications. Findings… (voir plus) suggest that there are opportunities to increase the patterns’ adoption in practice by raising awareness of such patterns within the community.
2022-03-01
Computer (published)
doi.org
The Role of Robotics in Achieving the United Nations Sustainable Development Goals - The Experts' Meeting at the 2021 IEEE/RSJ IROS Workshop [Industry Activities]
Vincent Mai
Bram Vanderborght
Tamás P. Haidegger
Alaa M. Khamis
Niraj Bhargava
Dominik B. O. Boesl
K. Gabriels
An Jacobs
AJung Moon
R. Murphy
Yasushi Nakauchi
Edson Prestes
Bhavani Rao R.
Ricardo Vinuesa
Carl-Maria Mörch
2022-03-01
IEEE Robotics Autom. Mag. (published)
doi.org
Multiscale PHATE identifies multimodal signatures of COVID-19
Manik Kuchroo
Je-chun Huang
Patrick W. Wong
Jean-Christophe Grenier
Dennis L. Shung
Alexander Tong
C. Lucas
J. Klein
Daniel B. Burkhardt
Scott Gigante
Abhinav Godavarthi
Bastian Rieck
Benjamin Israelow
Michael Simonov
Tianyang Mao
Ji Eun Oh
Julio Silva
Takehiro Takahashi
C. Odio
Arnau Casanovas‐massana … (voir 10 de plus)
John Byrne Fournier
Shelli F. Farhadian
C. D. Dela Cruz
A. Ko
Matthew Hirn
F. Wilson
Julie Hussin
Guy Wolf
Akiko Iwasaki
Smita Krishnaswamy
2022-02-28
Nature Biotechnology (published)
doi.org
Subgraph Retrieval Enhanced Model for Multi-hop Knowledge Base Question Answering
Jing Zhang
Xiaokang Zhang
Jifan Yu
Jian Tang
Jie Tang
Cuiping Li
Hong Chen
Recent works on knowledge base question answering (KBQA) retrieve subgraphs for easier reasoning. The desired subgraph is crucial as a small… (voir plus) one may exclude the answer but a large one might introduce more noises. However, the existing retrieval is either heuristic or interwoven with the reasoning, causing reasoning on the partial subgraphs, which increases the reasoning bias when the intermediate supervision is missing. This paper proposes a trainable subgraph retriever (SR) decoupled from the subsequent reasoning process, which enables a plug-and-play framework to enhance any subgraph-oriented KBQA model. Extensive experiments demonstrate SR achieves significantly better retrieval and QA performance than existing retrieval methods. Via weakly supervised pre-training as well as the end-to-end fine-tuning, SR achieves new state-of-the-art performance when combined with NSM (He et al., 2021), a subgraph-oriented reasoner, for embedding-based KBQA methods. Codes and datasets are available online (https://github.com/RUCKBReasoning/SubgraphRetrievalKBQA)
2022-02-27
ArXiv (preprint)
doi.org
arxiv.org
Healthsheet: Development of a Transparency Artifact for Health Datasets
Negar Rostamzadeh
Diana Mincu
Subhrajit Roy
Andrew J Smart
Lauren Wilcox
Mahima Pushkarna
Jessica Schrouff
Razvan Amironesei
Nyalleng Moorosi
Katherine Heller
Machine learning (ML) approaches have demonstrated promising results in a wide range of healthcare applications. Data plays a crucial role i… (voir plus)n developing ML-based healthcare systems that directly affect people’s lives. Many of the ethical issues surrounding the use of ML in healthcare stem from structural inequalities underlying the way we collect, use, and handle data. Developing guidelines to improve documentation practices regarding the creation, use, and maintenance of ML healthcare datasets is therefore of critical importance. In this work, we introduce Healthsheet, a contextualized adaptation of the original datasheet questionnaire [22] for health-specific applications. Through a series of semi-structured interviews, we adapt the datasheets for healthcare data documentation. As part of the Healthsheet development process and to understand the obstacles researchers face in creating datasheets, we worked with three publicly-available healthcare datasets as our case studies, each with different types of structured data: Electronic health Records (EHR), clinical trial study data, and smartphone-based performance outcome measures. Our findings from the interviewee study and case studies show 1) that datasheets should be contextualized for healthcare, 2) that despite incentives to adopt accountability practices such as datasheets, there is a lack of consistency in the broader use of these practices 3) how the ML for health community views datasheets and particularly Healthsheets as diagnostic tool to surface the limitations and strength of datasets and 4) the relative importance of different fields in the datasheet to healthcare concerns.
2022-02-26
ArXiv (preprint)
doi.org
arxiv.org
More Than Meets the Eye: Art Engages the Social Brain
Janneke E. P. van Leeuwen
Jeroen Boomgaard
Danilo Bzdok
S. Crutch
J. Warren
Here we present the viewpoint that art essentially engages the social brain, by demonstrating how art processing maps onto the social brain … (voir plus)connectome—the most comprehensive diagram of the neural dynamics that regulate human social cognition to date. We start with a brief history of the rise of neuroaesthetics as the scientific study of art perception and appreciation, in relation to developments in contemporary art practice and theory during the same period. Building further on a growing awareness of the importance of social context in art production and appreciation, we then set out how art engages the social brain and outline candidate components of the “artistic brain connectome.” We explain how our functional model for art as a social brain phenomenon may operate when engaging with artworks. We call for closer collaborations between the burgeoning field of neuroaesthetics and arts professionals, cultural institutions and diverse audiences in order to fully delineate and contextualize this model. Complementary to the unquestionable value of art for art’s sake, we argue that its neural grounding in the social brain raises important practical implications for mental health, and the care of people living with dementia and other neurological conditions.
2022-02-25
Frontiers in Neuroscience (published)
doi.org
Quantitative electrophysiological assessments as predictive markers of lower limb motor recovery after spinal cord injury: a pilot study with an adaptive trial design
Yin Nan Huang
El-Mehdi Meftah
Charlotte H. Pion
Jean-Marc Mac-Thiong
Julien Cohen-Adad
Dorothy Barthélemy
2022-02-24
Spinal Cord Series and Cases (publié)
doi.org