Publications

Evaluation of Categorical Generative Models - Bridging the Gap Between Real and Synthetic Data
Florence Regol
Anja Kroon
Mark Coates
The machine learning community has mainly relied on real data to benchmark algorithms as it provides compelling evidence of model applicabil… (see more)ity. Evaluation on synthetic datasets can be a powerful tool to provide a better understanding of a model’s strengths, weaknesses and overall capabilities. Gaining these insights can be particularly important for generative modeling as the target quantity is completely unknown. Multiple issues related to the evaluation of generative models have been reported in the literature. We argue those problems can be avoided by an evaluation based on ground truth. General criticisms of synthetic experiments are that they are too simplified and not representative of practical scenarios. As such, our experimental setting is tailored to a realistic generative task. We focus on categorical data and introduce an appropriately scalable evaluation method. Our method involves tasking a generative model to learn a distribution in a high-dimensional setting. We then successively bin the large space to obtain smaller probability spaces where meaningful statistical tests can be applied. We consider increasingly large probability spaces, which correspond to increasingly difficult modeling tasks, and compare the generative models based on the highest task difficulty they can reach before being detected as being too far from the ground truth. We validate our evaluation procedure with synthetic experiments on both synthetic generative models and current state-of-the-art categorical generative models.
2023-06-04
ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (published)
doi.org
arxiv.org
Fine-Tuning Strategies for Faster Inference Using Speech Self-Supervised Models: A Comparative Study
Salah Zaiem
Robin Algayres
Titouan Parcollet
Slim Essid
Mirco Ravanelli
Self-supervised learning (SSL) has allowed substantial progress in Automatic Speech Recognition (ASR) performance in low-resource settings. … (see more)In this context, it has been demonstrated that larger self-supervised feature extractors are crucial for achieving lower downstream ASR error rates. Thus, better performance might be sanctioned with longer inferences. This article explores different approaches that may be deployed during the fine-tuning to reduce the computations needed in the SSL encoder, leading to faster inferences. We adapt a number of existing techniques to common ASR settings and benchmark them, displaying performance drops and gains in inference times. Interestingly, we found that given enough downstream data, a simple downsampling of the input sequences outperforms the other methods with both low performance drops and high computational savings, reducing computations by 61.3% with an WER increase of only 0. 81. Finally, we analyze the robustness of the comparison to changes in dataset conditions, revealing sensitivity to dataset size.
2023-06-04
2023 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW) (published)
doi.org
arxiv.org
Self-Supervised Learning for Infant Cry Analysis
Arsenii Gorin
Cem Subakan
Sajjad Abdoli
Junhao Wang
Samantha Latremouille
Charles Onu
In this paper, we explore self-supervised learning (SSL) for analyzing a first-of-its-kind database of cry recordings containing clinical in… (see more)dications of more than a thousand newborns. Specifically, we target cry-based detection of neurological injury as well as identification of cry triggers such as pain, hunger, and discomfort. Annotating a large database in the medical setting is expensive and timeconsuming, typically requiring the collaboration of several experts over years. Leveraging large amounts of unlabeled audio data to learn useful representations can lower the cost of building robust models and, ultimately, clinical solutions. In this work, we experiment with self-supervised pre-training of a convolutional neural network on large audio datasets. We show that pre-training with SSL contrastive loss (SimCLR) performs significantly better than supervised pre-training for both neuro injury and cry triggers. In addition, we demonstrate further performance gains through SSL-based domain adaptation using unlabeled infant cries. We also show that using such SSL-based pre-training for adaptation to cry sounds decreases the need for labeled data of the overall system.
2023-06-04
2023 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW) (published)
doi.org
arxiv.org
ANSEL Photobot: A Robot Event Photographer with Semantic Intelligence
Dmitriy Rivkin
Gregory Dudek
Nikhil Kakodkar
David Meger
Oliver Limoyo
Xue (Steve) Liu
Francois Hogan
Our work examines the way in which large language models can be used for robotic planning and sampling in the context of automated photograp… (see more)hic documentation. Specifically, we illustrate how to produce a photo-taking robot with an exceptional level of semantic awareness by leveraging recent advances in general purpose language (LM) and vision-language (VLM) models. Given a high-level description of an event we use an LM to generate a natural-language list of photo descriptions that one would expect a photographer to capture at the event. We then use a VLM to identify the best matches to these descriptions in the robot's video stream. The photo portfolios generated by our method are consistently rated as more appropriate to the event by human evaluators than those generated by existing methods.
2023-06-02
2023 IEEE International Conference on Robotics and Automation (ICRA) (published)
doi.org
arxiv.org
Generating Stable and Collision-Free Policies through Lyapunov Function Learning
Alexandre Coulombe
Hsiu-Chin Lin
The need for rapid and reliable robot deployment is on the rise. Imitation Learning (IL) has become popular for producing motion planning po… (see more)licies from a set of demonstrations. However, many methods in IL are not guaranteed to produce stable policies. The generated policy may not converge to the robot target, reducing reliability, and may collide with its environment, reducing the safety of the system. Stable Estimator of Dynamic Systems (SEDS) produces stable policies by constraining the Lyapunov stability criteria during learning, but the Lyapunov candidate function had to be manually selected. In this work, we propose a novel method for learning a Lyapunov function and a collision-free policy using a single neural network model. The method can be equipped with an obstacle avoidance module for convex object pairs to guarantee no collisions. We demonstrated our method is capable of finding policies in several simulation environments and transfer to a real-world scenario.
2023-06-02
2023 IEEE International Conference on Robotics and Automation (ICRA) (published)
doi.org
arxiv.org
Improving Generalization in Task-oriented Dialogues with Workflows and Action Plans
Stefania Raimondo
Chris Pal
Xiaotian Liu
David Vazquez
Hector. Palacios
2023-06-02
ArXiv (preprint)
doi.org
arxiv.org
Predicting Time to and Average Quality of Future Offers for Kidney Transplant Candidates Declining a Current Deceased Donor Kidney Offer: A Retrospective Cohort Study
Jonathan Jalbert
Jean-Noel Weller
Pierre-Luc Boivin
Sylvain Lavigne
Mehdi Taobane
Mike Pieper
Andrea Lodi
Heloise Cardinal
2023-06-02
Canadian Journal of Kidney Health and Disease (published)
doi.org
Communication Load Balancing via Efficient Inverse Reinforcement Learning
Abhisek Konar
Di Wu
Yi Tian Xu
Seowoo Jang
Steve Liu
Gregory Dudek
Communication load balancing aims to balance the load between different available resources, and thus improve the quality of service for net… (see more)work systems. After formulating the load balancing (LB) as a Markov decision process problem, reinforcement learning (RL) has recently proven effective in addressing the LB problem. To leverage the benefits of classical RL for load balancing, however, we need an explicit reward definition. Engineering this reward function is challenging, because it involves the need for expert knowledge and there lacks a general consensus on the form of an optimal reward function. In this work, we tackle the communication load balancing problem from an inverse reinforcement learning (IRL) approach. To the best of our knowledge, this is the first time IRL has been successfully applied in the field of communication load balancing. Specifically, first, we infer a reward function from a set of demonstrations, and then learn a reinforcement learning load balancing policy with the inferred reward function. Compared to classical RL-based solution, the proposed solution can be more general and more suitable for real-world scenarios. Experimental evaluations implemented on different simulated traffic scenarios have shown our method to be effective and better than other baselines by a considerable margin.
2023-06-01
ICC 2023 - IEEE International Conference on Communications (published)
doi.org
arxiv.org
Discussion of “Experimental Study of the Thixotropic Strength Recovery and Microstructural Evolution of Marine Clays”
Xianwei Zhang
Xinyu Liu
Gang Wang
2023-06-01
Journal of Geotechnical and Geoenvironmental Engineering (published)
doi.org
Discussion of “Experimental Study of the Thixotropic Strength Recovery and Microstructural Evolution of Marine Clays”
Xianwei Zhang
Xinyu Liu
Gang Wang
2023-06-01
Journal of Geotechnical and Geoenvironmental Engineering (published)
doi.org
Estimating individual minimum calibration for deep-learning with predictive performance recovery: An example case of gait surface classification from wearable sensor gait data.
Guillaume Lam
Irina Rish
P. Dixon
2023-06-01
Journal of Biomechanics (published)
doi.org
Fast Fine-Tuning Using Curriculum Domain Adaptation
Lulan Shen
Ibtihel Amara
Ruofeng Li
Brett Meyer
Warren Gross
James J. Clark
Current deep neural networks (DNNs) have achieved remarkable accuracy in various downstream tasks. However, their training and fine-tuning a… (see more)re challenging due to several factors, such as limited computational resources, extended training and fine-tuning times, and over-fitting due to small datasets. To address these challenges, we propose a three-stage fast fine-tuning method that efficiently trains DNNs for edge devices. Our method combines curriculum learning and domain adaptation techniques to accelerate training while achieving comparable performance. First, we develop a data curriculum approach, which ranks the dataset according to difficulty and split it into the source domain (containing easy data) and the target domain (containing difficult data). Second, we adapt the pretrained model from the source domain to the target domain using an unsupervised domain adaptation (UDA) method called Deep CORAL. Finally, we continue training the adapted model on the source domain with fewer epochs. Our method achieves high accuracy quickly on various modern neural network architectures and datasets such as CIFAR-10, CIFAR-100, and CINIC-10.
2023-06-01
Canadian Conference on Computer and Robot Vision (published)
doi.org