482 citations · 1.4k across the 36 of their papers we have counts for
37 papers
A*HAR: A New Benchmark towards Semi-supervised learning for Class-imbalanced Human Activity Recognition
Govind Narasimman, Kangkang Lu, Arun Raja +4
Despite the vast literature on Human Activity Recognition (HAR) with wearable inertial sensor data, it is perhaps surprising that there are few studies investigating semisupervised…
Learning to Prune Deep Neural Networks via Reinforcement Learning
Manas Gupta, Siddharth Aravindan, Aleksandra Kalisz +2
This paper proposes PuRL - a deep reinforcement learning (RL) based algorithm for pruning neural networks. Unlike current RL based model compression approaches where feedback is gi…
Empirical Analysis of Overfitting and Mode Drop in GAN Training
Yasin Yazici, Chuan-Sheng Foo, Stefan Winkler +2
We examine two key questions in GAN training, namely overfitting and mode drop, from an empirical perspective. We show that when stochasticity is removed from the training procedur…
Classify and Generate: Using Classification Latent Space Representations for Image Generations
Saisubramaniam Gopalakrishnan, Pranshu Ranjan Singh, Yasin Yazici +3
Utilization of classification latent space information for downstream reconstruction and generation is an intriguing and a relatively unexplored area. In general, discriminative re…
FaultNet: Faulty Rail-Valves Detection using Deep Learning and Computer Vision
Ramanpreet Singh Pahwa, Jin Chao, Jestine Paul +7
Regular inspection of rail valves and engines is an important task to ensure the safety and efficiency of railway networks around the globe. Over the past decade, computer vision a…
A*3D Dataset: Towards Autonomous Driving in Challenging Environments
Quang-Hieu Pham, Pierre Sevestre, Ramanpreet Singh Pahwa +6
With the increasing global popularity of self-driving cars, there is an immediate need for challenging real-world datasets for benchmarking and training various computer vision tas…
Venn GAN: Discovering Commonalities and Particularities of Multiple Distributions
Yasin Yazıcı, Bruno Lecouat, Chuan-Sheng Foo +4
We propose a GAN design which models multiple distributions effectively and discovers their commonalities and particularities. Each data distribution is modeled with a mixture of $…
CaRENets: Compact and Resource-Efficient CNN for Homomorphic Inference on Encrypted Medical Images
Jin Chao, Ahmad Al Badawi, Balagopal Unnikrishnan +9
Convolutional neural networks (CNNs) have enabled significant performance leaps in medical image classification tasks. However, translating neural network models for clinical appli…
Dataflow-based Joint Quantization of Weights and Activations for Deep Neural Networks
Xue Geng, Jie Fu, Bin Zhao +4
This paper addresses a challenging problem - how to reduce energy consumption without incurring performance drop when deploying deep neural networks (DNNs) at the inference stage.…
Semi-Supervised Deep Learning for Abnormality Classification in Retinal Images
Bruno Lecouat, Ken Chang, Chuan-Sheng Foo +7
Supervised deep learning algorithms have enabled significant performance gains in medical image classification tasks. But these methods rely on large labeled datasets that require…
Adversarially Learned Anomaly Detection
Houssam Zenati, Manon Romain, Chuan Sheng Foo +2
Anomaly detection is a significant and hence well-studied problem. However, developing effective anomaly detection methods for complex and high-dimensional data remains a challenge…
Graph Convolutional Neural Networks for Polymers Property Prediction
Minggang Zeng, Jatin Nitin Kumar, Zeng Zeng +3
A fast and accurate predictive tool for polymer properties is demanding and will pave the way to iterative inverse design. In this work, we apply graph convolutional neural network…
Predicting thermoelectric properties from crystal graphs and material descriptors - first application for functional materials
Leo Laugier, Daniil Bash, Jose Recatala +5
We introduce the use of Crystal Graph Convolutional Neural Networks (CGCNN), Fully Connected Neural Networks (FCNN) and XGBoost to predict thermoelectric properties. The dataset fo…
Holistic Multi-modal Memory Network for Movie Question Answering
Anran Wang, Anh Tuan Luu, Chuan-Sheng Foo +3
Answering questions according to multi-modal context is a challenging problem as it requires a deep integration of different data sources. Existing approaches only employ partial i…
TEA-DNN: the Quest for Time-Energy-Accuracy Co-optimized Deep Neural Networks
Lile Cai, Anne-Maelle Barneche, Arthur Herbout +4
Embedded deep learning platforms have witnessed two simultaneous improvements. First, the accuracy of convolutional neural networks (CNNs) has been significantly improved through t…
Towards the AlexNet Moment for Homomorphic Encryption: HCNN, theFirst Homomorphic CNN on Encrypted Data with GPUs
Ahmad Al Badawi, Jin Chao, Jie Lin +6
Deep Learning as a Service (DLaaS) stands as a promising solution for cloud-based inference applications. In this setting, the cloud has a pre-learned model whereas the user has sa…
Deep Adaptive Temporal Pooling for Activity Recognition
Sibo Song, Ngai-Man Cheung, Vijay Chandrasekhar +1
Deep neural networks have recently achieved competitive accuracy for human activity recognition. However, there is room for improvement, especially in modeling long-term temporal i…
Manifold regularization with GANs for semi-supervised learning
Bruno Lecouat, Chuan-Sheng Foo, Houssam Zenati +1
Generative Adversarial Networks are powerful generative models that are able to model the manifold of natural images. We leverage this property to perform manifold regularization b…
Optimistic mirror descent in saddle-point problems: Going the extra (gradient) mile
Panayotis Mertikopoulos, Bruno Lecouat, Houssam Zenati +3
Owing to their connection with generative adversarial networks (GANs), saddle-point problems have recently attracted considerable interest in machine learning and beyond. By necess…
The Unusual Effectiveness of Averaging in GAN Training
Yasin Yazıcı, Chuan-Sheng Foo, Stefan Winkler +3
We examine two different techniques for parameter averaging in GAN training. Moving Average (MA) computes the time-average of parameters, whereas Exponential Moving Average (EMA) c…
Semi-Supervised Learning with GANs: Revisiting Manifold Regularization
Bruno Lecouat, Chuan-Sheng Foo, Houssam Zenati +1
GANS are powerful generative models that are able to model the manifold of natural images. We leverage this property to perform manifold regularization by approximating the Laplaci…
Accelerating Materials Development via Automation, Machine Learning, and High-Performance Computing
Juan Pablo Correa-Baena, Kedar Hippalgaonkar, Jeroen van Duren +6
Successful materials innovations can transform society. However, materials research often involves long timelines and low success probabilities, dissuading investors who have expec…
Online Deep Learning: Growing RBM on the fly
Savitha Ramasamy, Kanagasabai Rajaraman, Pavitra Krishnaswamy +1
We propose a novel online learning algorithm for Restricted Boltzmann Machines (RBM), namely, the Online Generative Discriminative Restricted Boltzmann Machine (OGD-RBM), that prov…
Efficient GAN-Based Anomaly Detection
Houssam Zenati, Chuan Sheng Foo, Bruno Lecouat +2
Generative adversarial networks (GANs) are able to model the complex highdimensional distributions of real-world data, which suggests they could be effective for anomaly detection.…