328 citations · 782 across the 45 of their papers we have counts for
49 papers
Revisit Multimodal Meta-Learning through the Lens of Multi-Task Learning
Milad Abdollahzadeh, Touba Malekzadeh, Ngai-Man Cheung
Multimodal meta-learning is a recent problem that extends conventional few-shot meta-learning by generalizing its setup to diverse multimodal task distributions. This setup makes a…
Measuring Fairness in Generative Models
Christopher T. H Teo, Ngai-Man Cheung
Deep generative models have made much progress in improving training stability and quality of generated data. Recently there has been increased interest in the fairness of deep-gen…
A Closer Look at Fourier Spectrum Discrepancies for CNN-generated Images Detection
Keshigeyan Chandrasegaran, Ngoc-Trung Tran, Ngai-Man Cheung
CNN-based generative modelling has evolved to produce synthetic images indistinguishable from real images in the RGB pixel space. Recent works have observed that CNN-generated imag…
Unsupervised Deep Cross-modality Spectral Hashing
Tuan Hoang, Thanh-Toan Do, Tam V. Nguyen +1
This paper presents a novel framework, namely Deep Cross-modality Spectral Hashing (DCSH), to tackle the unsupervised learning problem of binary hash codes for efficient cross-moda…
Explanation-Guided Training for Cross-Domain Few-Shot Classification
Jiamei Sun, Sebastian Lapuschkin, Wojciech Samek +3
Cross-domain few-shot classification task (CD-FSC) combines few-shot classification with the requirement to generalize across domains represented by datasets. This setup faces chal…
InfoMax-GAN: Improved Adversarial Image Generation via Information Maximization and Contrastive Learning
Kwot Sin Lee, Ngoc-Trung Tran, Ngai-Man Cheung
While Generative Adversarial Networks (GANs) are fundamental to many generative modelling applications, they suffer from numerous issues. In this work, we propose a principled fram…
On Data Augmentation for GAN Training
Ngoc-Trung Tran, Viet-Hung Tran, Ngoc-Bao Nguyen +2
Recent successes in Generative Adversarial Networks (GAN) have affirmed the importance of using more data in GAN training. Yet it is expensive to collect data in many domains such…
Self-supervised GAN: Analysis and Improvement with Multi-class Minimax Game
Ngoc-Trung Tran, Viet-Hung Tran, Ngoc-Bao Nguyen +2
Self-supervised (SS) learning is a powerful approach for representation learning using unlabeled data. Recently, it has been applied to Generative Adversarial Networks (GAN) traini…
Optimized Routing and Spectrum Assignment for Video Communication over an Elastic Optical Network
Hamed Alizadeh Ghazijahani, Hadi Seyedarabi, Javad Musevi Niya +1
Elastic optical network (EON) efficiently utilize spectral resources for optical fiber communication by allocating the minimum necessary bandwidth to client demands. On the other h…
TEAGS: Time-aware Text Embedding Approach to Generate Subgraphs
Saeid Hosseini, Saeed Najafipour, Ngai-Man Cheung +3
Contagions (e.g. virus, gossip) spread over the nodes in propagation graphs. We can use the temporal and textual data of the nodes to compute the edge weights and then generate sub…
An Improved Self-supervised GAN via Adversarial Training
Ngoc-Trung Tran, Viet-Hung Tran, Ngoc-Bao Nguyen +1
We propose to improve unconditional Generative Adversarial Networks (GAN) by training the self-supervised learning with the adversarial process. In particular, we apply self-superv…
Simultaneous Feature Aggregating and Hashing for Compact Binary Code Learning
Thanh-Toan Do, Khoa Le, Tuan Hoang +3
Representing images by compact hash codes is an attractive approach for large-scale content-based image retrieval. In most state-of-the-art hashing-based image retrieval systems, f…
SDRSAC: Semidefinite-Based Randomized Approach for Robust Point Cloud Registration without Correspondences
Huu Le, Thanh-Toan Do, Tuan Hoang +1
This paper presents a novel randomized algorithm for robust point cloud registration without correspondences. Most existing registration approaches require a set of putative corres…
Detecting Target-Area Link-Flooding DDoS Attacks using Traffic Analysis and Supervised Learning
Mostafa Rezazad, Matthias R. Brust, Mohammad Akbari +2
A novel class of extreme link-flooding DDoS (Distributed Denial of Service) attacks is designed to cut off entire geographical areas such as cities and even countries from the Inte…
On Sparse Graph Fourier Transform
Seyed Hamid Safavi, Manas Khatua, Ngai-Man Cheung +1
In this paper, we propose a new regression-based algorithm to compute Graph Fourier Transform (GFT). Our algorithm allows different regularizations to be included when computing th…
Improving GAN with neighbors embedding and gradient matching
Ngoc-Trung Tran, Tuan-Anh Bui, Ngai-Man Cheung
We propose two new techniques for training Generative Adversarial Networks (GANs). Our objectives are to alleviate mode collapse in GAN and improve the quality of the generated sam…
DOPING: Generative Data Augmentation for Unsupervised Anomaly Detection with GAN
Swee Kiat Lim, Yi Loo, Ngoc-Trung Tran +3
Recently, the introduction of the generative adversarial network (GAN) and its variants has enabled the generation of realistic synthetic samples, which has been used for enlarging…
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…
Defense Against Adversarial Attacks with Saak Transform
Sibo Song, Yueru Chen, Ngai-Man Cheung +1
Deep neural networks (DNNs) are known to be vulnerable to adversarial perturbations, which imposes a serious threat to DNN-based decision systems. In this paper, we propose to appl…
MCP: a Multi-Component learning machine to Predict protein secondary structure
Leila Khalatbari, Mohammad Reza Kangavari, Saeid Hosseini +2
The Gene or DNA sequence in every cell does not control genetic properties on its own; Rather, this is done through translation of DNA into protein and subsequent formation of a ce…
Efficient and Deep Person Re-Identification using Multi-Level Similarity
Yiluan Guo, Ngai-Man Cheung
Person Re-Identification (ReID) requires comparing two images of person captured under different conditions. Existing work based on neural networks often computes the similarity of…
Dist-GAN: An Improved GAN using Distance Constraints
Ngoc-Trung Tran, Tuan-Anh Bui, Ngai-Man Cheung
We introduce effective training algorithms for Generative Adversarial Networks (GAN) to alleviate mode collapse and gradient vanishing. In our system, we constrain the generator by…
Fine-grained wound tissue analysis using deep neural network
Hossein Nejati, Hamed Alizadeh Ghazijahani, Milad Abdollahzadeh +4
Tissue assessment for chronic wounds is the basis of wound grading and selection of treatment approaches. While several image processing approaches have been proposed for automatic…
Binary Constrained Deep Hashing Network for Image Retrieval without Manual Annotation
Thanh-Toan Do, Tuan Hoang, Dang-Khoa Le Tan +4
Learning compact binary codes for image retrieval task using deep neural networks has attracted increasing attention recently. However, training deep hashing networks for the task…