Narges Armanfard

navid.hassan-zadeh@mila.quebec

Navid hassan Zadeh

Doctorat - McGill

thi-kieu-khanh.ho@mila.quebec

Khanh Ho Ho

Doctorat - McGill

Google Scholar

Alexander Koran

Doctorat - McGill

alexander.koran@mila.quebec

Thomas Lai

Doctorat - McGill

thomas.lai@mila.quebec

Brian MacDonald

Maîtrise recherche - McGill

brian.macdonald@mila.quebec

Dario Morle

Doctorat - McGill

dario.morle@mila.quebec

Abhijeet Praveen

Maîtrise recherche - McGill

abhijeet.praveen@mila.quebec

dimitrios.sinodinos@mila.quebec

Aman Sidhu

Maîtrise recherche - McGill

aman.sidhu@mila.quebec

Doctorat - McGill

sareh.soleimani-gilakjani@mila.quebec

Google Scholar

Sareh Soleimani Gilakjani

Postdoctorat - McGill

Jack Wei

Maîtrise recherche - McGill

jack.wei@mila.quebec

Publications

Multistep networks for roll force prediction in hot strip rolling mill

Shuhong Shen

Denzel Guye

Xiaoping Ma

Stephen Yue

2022-02-28

Machine Learning with Applications (publié)

Deep Reinforcement Learning in Human Activity Recognition: A Survey

Bahareh Nikpour

Dimitrios Sinodinos

<div>Human activity recognition is a popular research field in computer vision that has already been widely studied. However, it is st… (voir plus)ill an active research field since it plays an important role in many current and emerging real world intelligent systems, like visual surveillance and human-computer interaction. Deep Reinforcement Learning (DRL) has recently been employed to address the activity recognition problem with various purposes, such as finding attention in video data or obtaining the best network structure. DRL-based human activity recognition has only been around for a short time, and it is a challenging, novel field[ of study. Therefore, to facilitate further research in this field, we have constructed a comprehensive survey on activity recognition methods that incorporate deep reinforcement learning. Towards the end of this survey, we summarize key challenges and open problems in this area that can be addressed by researchers in the future.</div>

2022-02-21

INDIGO (prépublication)

Deep Successive Subspace Learning for Data Clustering

Mohammadreza Sadeghi

Deep clustering combines embedding and clustering together to obtain an optimal low dimensional embedding sub- space (aka latent subspace) f… (voir plus)or clustering, which can be more effective compared to conventional clustering approaches such as k-means. Typical deep clustering methods employ autoencoder (AE) and obtain their optimal latent space through minimizing data reconstruction loss which has no substantial connection with the clustering performance. In contrast, in this paper we propose a novel AE-based clustering scheme Deep Successive Subspace Learning (DSSL) which simultaneously minimizes weighted reconstruction and clustering losses of data points, where weights are defined based on similarity between latent representation of data points and cluster centers. DSSL obtains its optimal latent space through K (i.e. number of clusters) successive training runs where each run corresponds to an individual cluster. At each run, DSSL focuses on reconstruction and clustering of those data points that are more likely to belong to the corresponding cluster; hence, implicitly training those network parameters that have more influence on that cluster. Experimental results on benchmark datasets demonstrate that the proposed DSSL method can significantly outperform state-of-the-art clustering approaches.

2021-12-31

International Joint Conference on Neural Networks (inconnu)

Joint Selection using Deep Reinforcement Learning for Skeleton-based Activity Recognition

Bahareh Nikpour

<div>Skeleton based human activity recognition has attracted lots of attention due to its wide range of applications. Skeleton data in… (voir plus)cludes two or three dimensional coordinates of body joints. All of the body joints are not effective in recognizing different activities, so finding key joints within a video and across different activities has a significant role in improving the performance. In this paper we propose a novel framework that performs joint selection in skeleton video frames for the purpose of human activity recognition. To this end, we formulate the joint selection problem as a Markov Decision Process (MDP) where we employ deep reinforcement learning to find the most informative joints per frame. The proposed joint selection method is a general framework that can be employed to improve human activity classification methods. Experimental results on two benchmark activity recognition data sets using three different classifiers demonstrate effectiveness of the proposed joint selection method.</div>

2021-12-31

IEEE International Conference on Systems, Man, and Cybernetics (inconnu)

Self-Supervised Acoustic Anomaly Detection Via Contrastive Learning.

Hadi Hojjati

We propose an acoustic anomaly detection algorithm based on the framework of contrastive learning. Contrastive learning is a recently propos… (voir plus)ed self-supervised approach that has shown promising results in image classification and speech recognition. However, its application in anomaly detection is underexplored. Earlier studies have demonstrated that it can achieve state-of-the-art performance in image anomaly detection, but its capability in anomalous sound detection is yet to be investigated. For the first time, we propose a contrastive learning-based framework that is suitable for acoustic anomaly detection. Since most existing contrastive learning approaches are targeted toward images, the effect of other data transformations on the performance of the algorithm is unknown. Our framework learns a representation from unlabeled data by applying audio-specific data augmentations. We show that in the resulting latent space, normal and abnormal points are distinguishable. Experiments conducted on the MIMII dataset confirm that our approach can outperform competing methods in detecting anomalies.

2021-12-31

IEEE International Conference on Acoustics, Speech and Signal Processing (inconnu)

Deep Clustering with Self-supervision using Pairwise Data Similarities

Mohammadreza Sadeghi

Deep clustering incorporates embedding into clustering to find a lower-dimensional space appropriate for clustering. Most of the existing me… (voir plus)thods try to group similar data points through simultaneously minimizing clustering and reconstruction losses, employing an autoencoder (AE). However, they all ignore the relevant useful information available within pairwise data relationships. In this paper we propose a novel deep clustering framework with self-supervision using pairwise data similarities (DCSS). The proposed method consists of two successive phases. First, we propose a novel AE-based approach that aims to aggregate similar data points near a common group center in the latent space of an AE. The AE's latent space is obtained by minimizing weighted reconstruction and centering losses of data points, where weights are defined based on similarity of data points and group centers. In the second phase, we map the AE's latent space, using a fully connected network MNet, onto a K-dimensional space used to derive the final data cluster assignments, where K is the number of clusters. MNet is trained to strengthen (weaken) similarity of similar (dissimilar) samples. Experimental results on multiple benchmark datasets demonstrate the effectiveness of DCSS for data clustering and as a general framework for boosting up state-of-the-art clustering methods.

2021-12-09

Figshare (prépublication)