328 citations · 782 across the 45 of their papers we have counts for
35 papers · 1 filter
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…
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…
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…
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…
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…
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…
Simultaneous Compression and Quantization: A Joint Approach for Efficient Unsupervised Hashing
Tuan Hoang, Thanh-Toan Do, Huu Le +2
For unsupervised data-dependent hashing, the two most important requirements are to preserve similarity in the low-dimensional feature space and to minimize the binary quantization…
On-device Scalable Image-based Localization via Prioritized Cascade Search and Fast One-Many RANSAC
Ngoc-Trung Tran, Dang-Khoa Le Tan, Anh-Dzung Doan +4
We present the design of an entire on-device system for large-scale urban localization using images. The proposed design integrates compact image retrieval and 2D-3D correspondence…
From Selective Deep Convolutional Features to Compact Binary Representations for Image Retrieval
Thanh-Toan Do, Tuan Hoang, Dang-Khoa Le Tan +3
In the large-scale image retrieval task, the two most important requirements are the discriminability of image representations and the efficiency in computation and storage of repr…
Aircraft Fuselage Defect Detection using Deep Neural Networks
Touba Malekzadeh, Milad Abdollahzadeh, Hossein Nejati +1
To ensure flight safety of aircraft structures, it is necessary to have regular maintenance using visual and nondestructive inspection (NDI) methods. In this paper, we propose an a…
Compact Hash Code Learning with Binary Deep Neural Network
Thanh-Toan Do, Tuan Hoang, Dang-Khoa Le Tan +2
Learning compact binary codes for image retrieval problem using deep neural networks has recently attracted increasing attention. However, training deep hashing networks is challen…
Accessible Melanoma Detection using Smartphones and Mobile Image Analysis
T. -T. Do, T. Hoang, V. Pomponiu +6
We investigate the design of an entire mobile imaging system for early detection of melanoma. Different from previous work, we focus on smartphone-captured visible light images. Ou…
Supervised Hashing with End-to-End Binary Deep Neural Network
Dang-Khoa Le Tan, Thanh-Toan Do, Ngai-Man Cheung
Image hashing is a popular technique applied to large scale content-based visual retrieval due to its compact and efficient binary codes. Our work proposes a new end-to-end deep ne…
Truly Multi-modal YouTube-8M Video Classification with Video, Audio, and Text
Zhe Wang, Kingsley Kuan, Mathieu Ravaut +13
The YouTube-8M video classification challenge requires teams to classify 0.7 million videos into one or more of 4,716 classes. In this Kaggle competition, we placed in the top 3% o…
Selective Deep Convolutional Features for Image Retrieval
Tuan Hoang, Thanh-Toan Do, Dang-Khoa Le Tan +1
Convolutional Neural Network (CNN) is a very powerful approach to extract discriminative local descriptors for effective image search. Recent work adopts fine-tuned strategies to f…