Search Results for author: Justin Dauwels

Found 26 papers, 4 papers with code

Extreme Precipitation Nowcasting using Transformer-based Generative Models

no code implementations6 Mar 2024 Cristian Meo, Ankush Roy, Mircea Lică, Junzhe Yin, Zeineb Bou Che, Yanbo Wang, Ruben Imhoff, Remko Uijlenhoet, Justin Dauwels

This paper presents an innovative approach to extreme precipitation nowcasting by employing Transformer-based generative models, namely NowcastingGPT with Extreme Value Loss (EVL) regularization.

Slot-VAE: Object-Centric Scene Generation with Slot Attention

no code implementations12 Jun 2023 Yanbo Wang, Letao Liu, Justin Dauwels

Slot attention has shown remarkable object-centric representation learning performance in computer vision tasks without requiring any supervision.

Object Representation Learning +1

MERLIon CCS Challenge Evaluation Plan

no code implementations31 May 2023 Leibny Paola Garcia Perera, Y. H. Victoria Chua, Hexin Liu, Fei Ting Woon, Andy W. H. Khong, Justin Dauwels, Sanjeev Khudanpur, Suzy J. Styles

This paper introduces the inaugural Multilingual Everyday Recordings- Language Identification on Code-Switched Child-Directed Speech (MERLIon CCS) Challenge, focused on developing robust language identification and language diarization systems that are reliable for non-standard, accented, spontaneous code-switched, child-directed speech collected via Zoom.

Language Identification Task 2

Investigating model performance in language identification: beyond simple error statistics

no code implementations30 May 2023 Suzy J. Styles, Victoria Y. H. Chua, Fei Ting Woon, Hexin Liu, Leibny Paola Garcia Perera, Sanjeev Khudanpur, Andy W. H. Khong, Justin Dauwels

These overview metrics do not provide information about model performance at the level of individual speakers, recordings, or units of speech with different linguistic characteristics.

Language Identification

MERLIon CCS Challenge: A English-Mandarin code-switching child-directed speech corpus for language identification and diarization

no code implementations30 May 2023 Victoria Y. H. Chua, Hexin Liu, Leibny Paola Garcia Perera, Fei Ting Woon, Jinyi Wong, Xiangyu Zhang, Sanjeev Khudanpur, Andy W. H. Khong, Justin Dauwels, Suzy J. Styles

To enhance the reliability and robustness of language identification (LID) and language diarization (LD) systems for heterogeneous populations and scenarios, there is a need for speech processing models to be trained on datasets that feature diverse language registers and speech patterns.

Language Identification

TC-VAE: Uncovering Out-of-Distribution Data Generative Factors

no code implementations8 Apr 2023 Cristian Meo, Anirudh Goyal, Justin Dauwels

We show that the proposed model is able to uncover OOD generative factors on different datasets and outperforms on average the related baselines in terms of downstream disentanglement metrics.

Disentanglement

PEM: Perception Error Model for Virtual Testing of Autonomous Vehicles

no code implementations23 Feb 2023 Andrea Piazzoni, Jim Cherian, Justin Dauwels, Lap-Pui Chau

In this article, we define Perception Error Models (PEM), a virtual simulation component that can enable the analysis of the impact of perception errors on AV safety, without the need to model the sensors themselves.

Autonomous Vehicles

CoPEM: Cooperative Perception Error Models for Autonomous Driving

no code implementations21 Nov 2022 Andrea Piazzoni, Jim Cherian, Roshan Vijay, Lap-Pui Chau, Justin Dauwels

In this paper, we introduce the notion of Cooperative Perception Error Models (coPEMs) towards achieving an effective and efficient integration of V2X solutions within a virtual test environment.

Autonomous Driving

Learning to Solve Multiple-TSP with Time Window and Rejections via Deep Reinforcement Learning

1 code implementation13 Sep 2022 Rongkai Zhang, Cong Zhang, Zhiguang Cao, Wen Song, Puay Siew Tan, Jie Zhang, Bihan Wen, Justin Dauwels

We propose a manager-worker framework based on deep reinforcement learning to tackle a hard yet nontrivial variant of Travelling Salesman Problem (TSP), \ie~multiple-vehicle TSP with time window and rejections (mTSPTWR), where customers who cannot be served before the deadline are subject to rejections.

Transformer Convolutional Neural Networks for Automated Artifact Detection in Scalp EEG

no code implementations4 Aug 2022 Wei Yan Peh, Yuanyuan Yao, Justin Dauwels

Next, for each of these five types of artifacts, we combine the output of these channel-wise detectors to detect artifacts in multi-channel EEG segments.

Artifact Detection Binary Classification +3

Enhance Language Identification using Dual-mode Model with Knowledge Distillation

1 code implementation7 Mar 2022 Hexin Liu, Leibny Paola Garcia Perera, Andy W. H. Khong, Justin Dauwels, Suzy J. Styles, Sanjeev Khudanpur

In this paper, we propose to employ a dual-mode framework on the x-vector self-attention (XSA-LID) model with knowledge distillation (KD) to enhance its language identification (LID) performance for both long and short utterances.

Knowledge Distillation Language Identification

R3L: Connecting Deep Reinforcement Learning to Recurrent Neural Networks for Image Denoising via Residual Recovery

no code implementations12 Jul 2021 Rongkai Zhang, Jiang Zhu, Zhiyuan Zha, Justin Dauwels, Bihan Wen

To benchmark the effectiveness of reinforcement learning in R3L, we train a recurrent neural network with the same architecture for residual recovery using the deterministic loss, thus to analyze how the two different training strategies affect the denoising performance.

Benchmarking Image Denoising +3

ADIS-GAN: Affine Disentangled GAN

no code implementations1 Jan 2021 Letao Liu, Martin Saerbeck, Justin Dauwels

This paper proposes Affine Disentangled GAN (ADIS-GAN), which is a Generative Adversarial Network that can explicitly disentangle affine transformations in a self-supervised and rigorous manner.

Generative Adversarial Network Inductive Bias +1

Efficient Variational Bayes Learning of Graphical Models with Smooth Structural Changes

no code implementations16 Sep 2020 Hang Yu, Songwei Wu, Justin Dauwels

Estimating time-varying graphical models are of paramount importance in various social, financial, biological, and engineering systems, since the evolution of such networks can be utilized for example to spot trends, detect anomalies, predict vulnerability, and evaluate the impact of interventions.

Time Series Analysis Variational Inference

On the Quality Requirements of Demand Prediction for Dynamic Public Transport

no code implementations31 Aug 2020 Inon Peled, Kelvin Lee, Yu Jiang, Justin Dauwels, Francisco C. Pereira

Our results suggest that the optimized performance is mainly affected by the skew of the noise distribution and the presence of infrequently large prediction errors.

Modeling Perception Errors towards Robust Decision Making in Autonomous Vehicles

no code implementations31 Jan 2020 Andrea Piazzoni, Jim Cherian, Martin Slavik, Justin Dauwels

Sensing and Perception (S&P) is a crucial component of an autonomous system (such as a robot), especially when deployed in highly dynamic environments where it is required to react to unexpected situations.

Autonomous Vehicles Decision Making

Factored Latent-Dynamic Conditional Random Fields for Single and Multi-label Sequence Modeling

1 code implementation9 Nov 2019 Satyajit Neogi, Justin Dauwels

In addition, LSTM based models display inconsistent performance across validation and test data, and pose diffculty to select models on validation data during our experiments.

Model Selection

Online Predictive Optimization Framework for Stochastic Demand-Responsive Transit Services

no code implementations26 Feb 2019 Inon Peled, Kelvin Lee, Yu Jiang, Justin Dauwels, Francisco C. Pereira

This study develops an online predictive optimization framework for dynamically operating a transit service in an area of crowd movements.

Autonomous Vehicles

Actor-Action Semantic Segmentation with Region Masks

no code implementations23 Jul 2018 Kang Dang, Chunluan Zhou, Zhigang Tu, Michael Hoy, Justin Dauwels, Junsong Yuan

One major challenge for this task is that when an actor performs an action, different body parts of the actor provide different types of cues for the action category and may receive inconsistent action labeling when they are labeled independently.

Action Segmentation Instance Segmentation +2

Multi-atomic Annealing Heuristic for Static Dial-a-ride Problem

no code implementations29 Jun 2018 Song Guang Ho, Ramesh Ramasamy Pandi, Sarat Chandra Nagavarapu, Justin Dauwels

It is observed that MATA attains a first feasible solution 29. 8 to 65. 1% faster, and obtains a final solution that is 3. 9 to 5. 2% better, when compared to other algorithms within 60 sec.

An Improved Tabu Search Heuristic for Static Dial-A-Ride Problem

no code implementations25 Jan 2018 Songguang Ho, Sarat Chandra Nagavarapu, Ramesh Ramasamy Pandi, Justin Dauwels

Multi-vehicle routing has become increasingly important with the rapid development of autonomous vehicle technology.

Scheduling

Neurology-as-a-Service for the Developing World

no code implementations16 Nov 2017 Tejas Dharamsi, Payel Das, Tejaswini Pedapati, Gregory Bramble, Vinod Muthusamy, Horst Samulowitz, Kush R. Varshney, Yuvaraj Rajamanickam, John Thomas, Justin Dauwels

In this work, we present a cloud-based deep neural network approach to provide decision support for non-specialist physicians in EEG analysis and interpretation.

EEG Electroencephalogram (EEG) +1

Cannot find the paper you are looking for? You can Submit a new open access paper.