Search Results for author: Ngai-Man Cheung

Found 69 papers, 25 papers with code

A Survey on Generative Modeling with Limited Data, Few Shots, and Zero Shot

1 code implementation26 Jul 2023 Milad Abdollahzadeh, Touba Malekzadeh, Christopher T. H. Teo, Keshigeyan Chandrasegaran, Guimeng Liu, Ngai-Man Cheung

In machine learning, generative modeling aims to learn to generate new data statistically similar to the training data distribution.

AdAM: Few-Shot Image Generation via Adaptation-Aware Kernel Modulation

no code implementations4 Jul 2023 Yunqing Zhao, Keshigeyan Chandrasegaran, Milad Abdollahzadeh, Chao Du, Tianyu Pang, Ruoteng Li, Henghui Ding, Ngai-Man Cheung

However, a major limitation of existing methods is that their knowledge preserving criteria consider only source domain/task and fail to consider target domain/adaptation in selecting source knowledge, casting doubt on their suitability for setups of different proximity between source and target domain.

Domain Adaptation Image Generation

On Evaluating Adversarial Robustness of Large Vision-Language Models

1 code implementation NeurIPS 2023 Yunqing Zhao, Tianyu Pang, Chao Du, Xiao Yang, Chongxuan Li, Ngai-Man Cheung, Min Lin

Large vision-language models (VLMs) such as GPT-4 have achieved unprecedented performance in response generation, especially with visual inputs, enabling more creative and adaptable interaction than large language models such as ChatGPT.

Adversarial Robustness multimodal generation +1

Exploring Incompatible Knowledge Transfer in Few-shot Image Generation

1 code implementation CVPR 2023 Yunqing Zhao, Chao Du, Milad Abdollahzadeh, Tianyu Pang, Min Lin, Shuicheng Yan, Ngai-Man Cheung

To this end, we propose knowledge truncation to mitigate this issue in FSIG, which is a complementary operation to knowledge preservation and is implemented by a lightweight pruning-based method.

Image Generation Transfer Learning

A Recipe for Watermarking Diffusion Models

1 code implementation17 Mar 2023 Yunqing Zhao, Tianyu Pang, Chao Du, Xiao Yang, Ngai-Man Cheung, Min Lin

Diffusion models (DMs) have demonstrated advantageous potential on generative tasks.

Fair Generative Models via Transfer Learning

1 code implementation2 Dec 2022 Christopher TH Teo, Milad Abdollahzadeh, Ngai-Man Cheung

We find that our fairTL can learn expressive sample generation during pre-training, thanks to the large (biased) dataset.

Fairness Transfer Learning

Few-shot Image Generation via Adaptation-Aware Kernel Modulation

2 code implementations29 Oct 2022 Yunqing Zhao, Keshigeyan Chandrasegaran, Milad Abdollahzadeh, Ngai-Man Cheung

However, a major limitation of existing methods is that their knowledge preserving criteria consider only source domain/source task, and they fail to consider target domain/adaptation task in selecting source model's knowledge, casting doubt on their suitability for setups of different proximity between source and target domain.

10-shot image generation Domain Adaptation +2

Discovering Transferable Forensic Features for CNN-generated Images Detection

1 code implementation24 Aug 2022 Keshigeyan Chandrasegaran, Ngoc-Trung Tran, Alexander Binder, Ngai-Man Cheung

Visual counterfeits are increasingly causing an existential conundrum in mainstream media with rapid evolution in neural image synthesis methods.

Image Forensics Image Generation

FS-BAN: Born-Again Networks for Domain Generalization Few-Shot Classification

1 code implementation23 Aug 2022 Yunqing Zhao, Ngai-Man Cheung

This improved generalization motivates us to study BAN for DG-FSC, and we show that BAN is promising to address the domain shift encountered in DG-FSC.

Domain Generalization Knowledge Distillation +1

Neural Correlates of Face Familiarity Perception

no code implementations31 Jul 2022 Evan Ehrenberg, Kleovoulos Leo Tsourides, Hossein Nejati, Ngai-Man Cheung, Pawan Sinha

In the domain of face recognition, there exists a puzzling timing discrepancy between results from macaque neurophysiology on the one hand and human electrophysiology on the other.

EEG Electroencephalogram (EEG) +1

Revisiting Label Smoothing and Knowledge Distillation Compatibility: What was Missing?

1 code implementation29 Jun 2022 Keshigeyan Chandrasegaran, Ngoc-Trung Tran, Yunqing Zhao, Ngai-Man Cheung

Critically, there is no effort to understand and resolve these contradictory findings, leaving the primal question -- to smooth or not to smooth a teacher network?

Image Classification Knowledge Distillation +1

A Closer Look at Few-shot Image Generation

no code implementations CVPR 2022 Yunqing Zhao, Henghui Ding, Houjing Huang, Ngai-Man Cheung

Informed by our analysis and to slow down the diversity degradation of the target generator during adaptation, our second contribution proposes to apply mutual information (MI) maximization to retain the source domain's rich multi-level diversity information in the target domain generator.

10-shot image generation Contrastive Learning +1

Graph-wise Common Latent Factor Extraction for Unsupervised Graph Representation Learning

1 code implementation16 Dec 2021 Thilini Cooray, Ngai-Man Cheung

Hence, this work proposes a new principle for unsupervised graph representation learning: Graph-wise Common latent Factor EXtraction (GCFX).

Graph Embedding Graph Generation +4

Multi-Modal Mutual Information Maximization: A Novel Approach for Unsupervised Deep Cross-Modal Hashing

no code implementations13 Dec 2021 Tuan Hoang, Thanh-Toan Do, Tam V. Nguyen, Ngai-Man Cheung

First, to learn informative representations that can preserve both intra- and inter-modal similarities, we leverage the recent advances in estimating variational lower-bound of MI to maximize the MI between the binary representations and input features and between binary representations of different modalities.

Cross-Modal Retrieval Retrieval

Revisit Multimodal Meta-Learning through the Lens of Multi-Task Learning

1 code implementation NeurIPS 2021 Milad Abdollahzadeh, Touba Malekzadeh, Ngai-Man Cheung

Second, inspired by hard parameter sharing in multi-task learning and a new interpretation of related work, we propose a new multimodal meta-learner that outperforms existing work by considerable margins.

Meta-Learning Multi-Task Learning

Towards A Conceptually Simple Defensive Approach for Few-shot classifiers Against Adversarial Support Samples

no code implementations24 Oct 2021 Yi Xiang Marcus Tan, Penny Chong, Jiamei Sun, Ngai-Man Cheung, Yuval Elovici, Alexander Binder

In this work, we aim to close this gap by studying a conceptually simple approach to defend few-shot classifiers against adversarial attacks.

To Smooth or not to Smooth? On Compatibility between Label Smoothing and Knowledge Distillation

no code implementations29 Sep 2021 Keshigeyan Chandrasegaran, Ngoc-Trung Tran, Yunqing Zhao, Ngai-Man Cheung

On the contrary, Shen et al. [2] claim that LS enlarges the distance between semantically similar classes; therefore a LS-trained teacher is compatible with KD.

Image Classification Knowledge Distillation +1

Measuring Fairness in Generative Models

1 code implementation16 Jul 2021 Christopher T. H Teo, Ngai-Man Cheung

Deep generative models have made much progress in improving training stability and quality of generated data.

Fairness

Shell Theory: A Statistical Model of Reality

1 code implementation IEEE Transactions on Pattern Analysis and Machine Intelligence 2021 Wen-Yan Lin, Siying Liu, Changhao Ren, Ngai-Man Cheung, Hongdong Li, Yasuyuki Matsushita

The foundational assumption of machine learning is that the data under consideration is separable into classes; while intuitively reasonable, separability constraints have proven remarkably difficult to formulate mathematically.

Anomaly Detection BIG-bench Machine Learning +6

Direct Quantization for Training Highly Accurate Low Bit-width Deep Neural Networks

no code implementations26 Dec 2020 Tuan Hoang, Thanh-Toan Do, Tam V. Nguyen, Ngai-Man Cheung

With this approach, we can learn activation quantizers that minimize the quantization errors in the majority of channels.

Image Classification Quantization

Detection of Adversarial Supports in Few-shot Classifiers Using Self-Similarity and Filtering

no code implementations9 Dec 2020 Yi Xiang Marcus Tan, Penny Chong, Jiamei Sun, Ngai-Man Cheung, Yuval Elovici, Alexander Binder

In this work, we propose a detection strategy to identify adversarial support sets, aimed at destroying the understanding of a few-shot classifier for a certain class.

Toward Scalable and Unified Example-based Explanation and Outlier Detection

no code implementations11 Nov 2020 Penny Chong, Ngai-Man Cheung, Yuval Elovici, Alexander Binder

We compare performances in terms of the classification, explanation quality, and outlier detection of our proposed network with other baselines.

Decision Making Outlier Detection

Unsupervised Deep Cross-modality Spectral Hashing

no code implementations1 Aug 2020 Tuan Hoang, Thanh-Toan Do, Tam V. Nguyen, Ngai-Man Cheung

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-modal retrieval.

Cross-Modal Retrieval Retrieval +1

Explanation-Guided Training for Cross-Domain Few-Shot Classification

1 code implementation17 Jul 2020 Jiamei Sun, Sebastian Lapuschkin, Wojciech Samek, Yunqing Zhao, Ngai-Man Cheung, Alexander Binder

It leverages on the explanation scores, obtained from existing explanation methods when applied to the predictions of FSC models, computed for intermediate feature maps of the models.

Classification Cross-Domain Few-Shot +1

InfoMax-GAN: Improved Adversarial Image Generation via Information Maximization and Contrastive Learning

1 code implementation9 Jul 2020 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.

Contrastive Learning Image Generation

On Data Augmentation for GAN Training

1 code implementation9 Jun 2020 Ngoc-Trung Tran, Viet-Hung Tran, Ngoc-Bao Nguyen, Trung-Kien Nguyen, Ngai-Man Cheung

We provide theoretical analysis to show that using our proposed DAG aligns with the original GAN in minimizing the Jensen-Shannon (JS) divergence between the original distribution and model distribution.

Data Augmentation

Few-Shot Regression via Learning Sparsifying Basis Functions

no code implementations25 Sep 2019 Yi Loo, Yiluan Guo, Ngai-Man Cheung

Recent few-shot learning algorithms have enabled models to quickly adapt to new tasks based on only a few training samples.

Few-Shot Learning regression

TEAGS: Time-aware Text Embedding Approach to Generate Subgraphs

no code implementations6 Jul 2019 Saeid Hosseini, Saeed Najafipour, Ngai-Man Cheung, Hongzhi Yin, Mohammad Reza Kangavari, Xiaofang Zhou

We can use the temporal and textual data of the nodes to compute the edge weights and then generate subgraphs with highly relevant nodes.

An Improved Self-supervised GAN via Adversarial Training

no code implementations14 May 2019 Ngoc-Trung Tran, Viet-Hung Tran, Ngoc-Bao Nguyen, Ngai-Man Cheung

Importantly, we find out that simultaneously training the discriminator to classify the fake class from the pseudo-classes of real samples for the classification task will improve the discriminator and subsequently lead better guides to train generator.

Classification General Classification +1

SDRSAC: Semidefinite-Based Randomized Approach for Robust Point Cloud Registration without Correspondences

1 code implementation6 Apr 2019 Huu Le, Thanh-Toan Do, Tuan Hoang, Ngai-Man Cheung

In particular, our work enables the use of randomized methods for point cloud registration without the need of putative correspondences.

Graph Matching Point Cloud Registration

Few-Shot Regression via Learned Basis Functions

no code implementations ICLR Workshop LLD 2019 Yi Loo, Swee Kiat Lim, Gemma Roig, Ngai-Man Cheung

We show that our model outperforms the current state of the art meta-learning methods in various regression tasks.

Few-Shot Learning regression

Detecting Target-Area Link-Flooding DDoS Attacks using Traffic Analysis and Supervised Learning

no code implementations1 Mar 2019 Mostafa Rezazad, Matthias R. Brust, Mohammad Akbari, Pascal Bouvry, Ngai-Man Cheung

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 Internet by simultaneously targeting a selected set of network links.

BIG-bench Machine Learning

Improving GAN with neighbors embedding and gradient matching

1 code implementation4 Nov 2018 Ngoc-Trung Tran, Tuan-Anh Bui, Ngai-Man Cheung

Second, we propose a new technique, gradient matching, to align the distributions of the generated samples and the real samples.

DOPING: Generative Data Augmentation for Unsupervised Anomaly Detection with GAN

no code implementations23 Aug 2018 Swee Kiat Lim, Yi Loo, Ngoc-Trung Tran, Ngai-Man Cheung, Gemma Roig, Yuval Elovici

To the best of our knowledge, our method is the first data augmentation technique focused on improving performance in unsupervised anomaly detection.

Data Augmentation Generative Adversarial Network +1

Deep Adaptive Temporal Pooling for Activity Recognition

no code implementations22 Aug 2018 Sibo Song, Ngai-Man Cheung, Vijay Chandrasekhar, Bappaditya Mandal

Specifically, using frame-level features, DATP regresses importance of different temporal segments and generates weights for them.

Human Activity Recognition

Defense Against Adversarial Attacks with Saak Transform

no code implementations6 Aug 2018 Sibo Song, Yueru Chen, Ngai-Man Cheung, C. -C. Jay Kuo

Therefore, we propose a Saak transform based preprocessing method with three steps: 1) transforming an input image to a joint spatial-spectral representation via the forward Saak transform, 2) apply filtering to its high-frequency components, and, 3) reconstructing the image via the inverse Saak transform.

Adversarial Defense

Efficient and Deep Person Re-Identification using Multi-Level Similarity

no code implementations CVPR 2018 Yiluan Guo, Ngai-Man Cheung

In this work, we propose an efficient, end-to-end fully convolutional Siamese network that computes the similarities at multiple levels.

Person Re-Identification

Fine-grained wound tissue analysis using deep neural network

no code implementations28 Feb 2018 Hossein Nejati, Hamed Alizadeh Ghazijahani, Milad Abdollahzadeh, Tooba Malekzadeh, Ngai-Man Cheung, Kheng Hock Lee, Lian Leng Low

In particular, seemingly, all previous approaches have assumed only 3 tissue types in the chronic wounds, while these wounds commonly exhibit 7 distinct tissue types that presence of each one changes the treatment procedure.

General Classification

Binary Constrained Deep Hashing Network for Image Retrieval without Manual Annotation

no code implementations21 Feb 2018 Thanh-Toan Do, Tuan Hoang, Dang-Khoa Le Tan, Trung Pham, Huu Le, Ngai-Man Cheung, Ian Reid

However, training deep hashing networks for the task is challenging due to the binary constraints on the hash codes, the similarity preserving property, and the requirement for a vast amount of labelled images.

Deep Hashing Image Retrieval +1

Simultaneous Compression and Quantization: A Joint Approach for Efficient Unsupervised Hashing

no code implementations19 Feb 2018 Tuan Hoang, Thanh-Toan Do, Huu Le, Dang-Khoa Le-Tan, Ngai-Man Cheung

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 loss.

Image Retrieval Quantization +1

On-device Scalable Image-based Localization via Prioritized Cascade Search and Fast One-Many RANSAC

no code implementations10 Feb 2018 Ngoc-Trung Tran, Dang-Khoa Le Tan, Anh-Dzung Doan, Thanh-Toan Do, Tuan-Anh Bui, Mengxuan Tan, Ngai-Man Cheung

In order to overcome the resource constraints of mobile devices, we propose a system design that leverages the scalability advantage of image retrieval and accuracy of 3D model-based localization.

Image-Based Localization Image Retrieval +2

From Selective Deep Convolutional Features to Compact Binary Representations for Image Retrieval

1 code implementation7 Feb 2018 Thanh-Toan Do, Tuan Hoang, Dang-Khoa Le Tan, Huu Le, Tam V. Nguyen, Ngai-Man Cheung

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 representations.

Image Retrieval Retrieval

Early detection of Crossfire attacks using deep learning

no code implementations31 Dec 2017 Saurabh Misra, Mengxuan Tan, Mostafa Rezazad, Matthias R. Brust, Ngai-Man Cheung

The adoption of benign traffic, while simultaneously targeting multiple network links, makes the detection of the Crossfire attack a serious challenge.

Cryptography and Security

Aircraft Fuselage Defect Detection using Deep Neural Networks

no code implementations26 Dec 2017 Touba Malekzadeh, Milad Abdollahzadeh, Hossein Nejati, Ngai-Man Cheung

To ensure flight safety of aircraft structures, it is necessary to have regular maintenance using visual and nondestructive inspection (NDI) methods.

Defect Detection

Compact Hash Code Learning with Binary Deep Neural Network

no code implementations8 Dec 2017 Thanh-Toan Do, Tuan Hoang, Dang-Khoa Le Tan, Anh-Dzung Doan, Ngai-Man Cheung

This design has overcome a challenging problem in some previous works: optimizing non-smooth objective functions because of binarization.

Binarization Deep Hashing +1

Adaptive Quantization for Deep Neural Network

no code implementations4 Dec 2017 Yiren Zhou, Seyed-Mohsen Moosavi-Dezfooli, Ngai-Man Cheung, Pascal Frossard

First, we propose a measurement to estimate the effect of parameter quantization errors in individual layers on the overall model prediction accuracy.

Quantization

Supervised Hashing with End-to-End Binary Deep Neural Network

no code implementations24 Nov 2017 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.

Image Retrieval Retrieval

Selective Deep Convolutional Features for Image Retrieval

1 code implementation4 Jul 2017 Tuan Hoang, Thanh-Toan Do, Dang-Khoa Le Tan, Ngai-Man Cheung

Recent work adopts fine-tuned strategies to further improve the discriminative power of the descriptors.

Image Retrieval Retrieval

Deep neural networks on graph signals for brain imaging analysis

no code implementations13 May 2017 Yiluan Guo, Hossein Nejati, Ngai-Man Cheung

In particular, our work proposes a new deep neural network design that integrates graph information such as brain connectivity with fully-connected layers.

EEG Electroencephalogram (EEG)

Simultaneous Low-rank Component and Graph Estimation for High-dimensional Graph Signals: Application to Brain Imaging

no code implementations26 Sep 2016 Rui Liu, Hossein Nejati, Seyed Hamid Safavi, Ngai-Man Cheung

We propose an algorithm to uncover the intrinsic low-rank component of a high-dimensional, graph-smooth and grossly-corrupted dataset, under the situations that the underlying graph is unknown.

General Classification

Binary Hashing with Semidefinite Relaxation and Augmented Lagrangian

no code implementations19 Jul 2016 Thanh-Toan Do, Anh-Dzung Doan, Duc-Thanh Nguyen, Ngai-Man Cheung

This paper proposes two approaches for inferencing binary codes in two-step (supervised, unsupervised) hashing.

Learning to Hash with Binary Deep Neural Network

no code implementations18 Jul 2016 Thanh-Toan Do, Anh-Dzung Doan, Ngai-Man Cheung

Our resulting optimization with these binary, independence, and balance constraints is difficult to solve.

Binarization

Embedding based on function approximation for large scale image search

no code implementations23 May 2016 Thanh-Toan Do, Ngai-Man Cheung

The objective of this paper is to design an embedding method that maps local features describing an image (e. g. SIFT) to a higher dimensional representation useful for the image retrieval problem.

Image Retrieval Retrieval

Egocentric Activity Recognition with Multimodal Fisher Vector

no code implementations25 Jan 2016 Sibo Song, Ngai-Man Cheung, Vijay Chandrasekhar, Bappaditya Mandal, Jie Lin

With the increasing availability of wearable devices, research on egocentric activity recognition has received much attention recently.

Egocentric Activity Recognition

Discrete Hashing with Deep Neural Network

no code implementations28 Aug 2015 Thanh-Toan Do, Anh-Zung Doan, Ngai-Man Cheung

This paper addresses the problem of learning binary hash codes for large scale image search by proposing a novel hashing method based on deep neural network.

Image Retrieval

FAemb: A Function Approximation-Based Embedding Method for Image Retrieval

no code implementations CVPR 2015 Thanh-Toan Do, Quang D. Tran, Ngai-Man Cheung

The embedded vectors resulted by the function approximation process are then aggregated to form a single representation used in the image retrieval framework.

Image Retrieval Retrieval

TOP-SPIN: TOPic discovery via Sparse Principal component INterference

no code implementations4 Nov 2013 Martin Takáč, Selin Damla Ahipaşaoğlu, Ngai-Man Cheung, Peter Richtárik

Our approach attacks the maximization problem in sparse PCA directly and is scalable to high-dimensional data.

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