34 citations · 114 across the 22 of their papers we have counts for
22 papers
AIR: Zero-shot Generative Model Adaptation with Iterative Refinement
Guimeng Liu, Milad Abdollahzadeh, Ngai-Man Cheung
Zero-shot generative model adaptation (ZSGM) aims to adapt a pre-trained generator to a target domain using only text guidance and without any samples from the target domain. Centr…
FairQueue: Rethinking Prompt Learning for Fair Text-to-Image Generation
Christopher T. H Teo, Milad Abdollahzadeh, Xinda Ma +1
Recently, prompt learning has emerged as the state-of-the-art (SOTA) for fair text-to-image (T2I) generation. Specifically, this approach leverages readily available reference imag…
Model Inversion Robustness: Can Transfer Learning Help?
Sy-Tuyen Ho, Koh Jun Hao, Keshigeyan Chandrasegaran +2
Model Inversion (MI) attacks aim to reconstruct private training data by abusing access to machine learning models. Contemporary MI attacks have achieved impressive attack performa…
Label-Only Model Inversion Attacks via Knowledge Transfer
Ngoc-Bao Nguyen, Keshigeyan Chandrasegaran, Milad Abdollahzadeh +1
In a model inversion (MI) attack, an adversary abuses access to a machine learning (ML) model to infer and reconstruct private training data. Remarkable progress has been made in t…
On Measuring Fairness in Generative Models
Christopher T. H. Teo, Milad Abdollahzadeh, Ngai-Man Cheung
Recently, there has been increased interest in fair generative models. In this work, we conduct, for the first time, an in-depth study on fairness measurement, a critical component…
A Survey on Generative Modeling with Limited Data, Few Shots, and Zero Shot
Milad Abdollahzadeh, Guimeng Liu, Touba Malekzadeh +3
Generative modeling in machine learning aims to synthesize new data samples that are statistically similar to those observed during training. While conventional generative models s…
AdAM: Few-Shot Image Generation via Adaptation-Aware Kernel Modulation
Yunqing Zhao, Keshigeyan Chandrasegaran, Milad Abdollahzadeh +5
Few-shot image generation (FSIG) aims to learn to generate new and diverse images given few (e.g., 10) training samples. Recent work has addressed FSIG by leveraging a GAN pre-trai…
On Evaluating Adversarial Robustness of Large Vision-Language Models
Yunqing Zhao, Tianyu Pang, Chao Du +4
Large vision-language models (VLMs) such as GPT-4 have achieved unprecedented performance in response generation, especially with visual inputs, enabling more creative and adaptabl…
Exploring Incompatible Knowledge Transfer in Few-shot Image Generation
Yunqing Zhao, Chao Du, Milad Abdollahzadeh +4
Few-shot image generation (FSIG) learns to generate diverse and high-fidelity images from a target domain using a few (e.g., 10) reference samples. Existing FSIG methods select, pr…
Re-thinking Model Inversion Attacks Against Deep Neural Networks
Ngoc-Bao Nguyen, Keshigeyan Chandrasegaran, Milad Abdollahzadeh +1
Model inversion (MI) attacks aim to infer and reconstruct private training data by abusing access to a model. MI attacks have raised concerns about the leaking of sensitive informa…
A Recipe for Watermarking Diffusion Models
Yunqing Zhao, Tianyu Pang, Chao Du +3
Diffusion models (DMs) have demonstrated advantageous potential on generative tasks. Widespread interest exists in incorporating DMs into downstream applications, such as producing…
Fair Generative Models via Transfer Learning
Christopher TH Teo, Milad Abdollahzadeh, Ngai-Man Cheung
This work addresses fair generative models. Dataset biases have been a major cause of unfairness in deep generative models. Previous work had proposed to augment large, biased data…
Few-shot Image Generation via Adaptation-Aware Kernel Modulation
Yunqing Zhao, Keshigeyan Chandrasegaran, Milad Abdollahzadeh +1
Few-shot image generation (FSIG) aims to learn to generate new and diverse samples given an extremely limited number of samples from a domain, e.g., 10 training samples. Recent wor…
Discovering Transferable Forensic Features for CNN-generated Images Detection
Keshigeyan Chandrasegaran, Ngoc-Trung Tran, Alexander Binder +1
Visual counterfeits are increasingly causing an existential conundrum in mainstream media with rapid evolution in neural image synthesis methods. Though detection of such counterfe…
FS-BAN: Born-Again Networks for Domain Generalization Few-Shot Classification
Yunqing Zhao, Ngai-Man Cheung
Conventional Few-shot classification (FSC) aims to recognize samples from novel classes given limited labeled data. Recently, domain generalization FSC (DG-FSC) has been proposed w…
Revisiting Label Smoothing and Knowledge Distillation Compatibility: What was Missing?
Keshigeyan Chandrasegaran, Ngoc-Trung Tran, Yunqing Zhao +1
This work investigates the compatibility between label smoothing (LS) and knowledge distillation (KD). Contemporary findings addressing this thesis statement take dichotomous stand…
A Closer Look at Few-shot Image Generation
Yunqing Zhao, Henghui Ding, Houjing Huang +1
Modern GANs excel at generating high quality and diverse images. However, when transferring the pretrained GANs on small target data (e.g., 10-shot), the generator tends to replica…
Multi-Modal Mutual Information Maximization: A Novel Approach for Unsupervised Deep Cross-Modal Hashing
Tuan Hoang, Thanh-Toan Do, Tam V. Nguyen +1
In this paper, we adopt the maximizing mutual information (MI) approach to tackle the problem of unsupervised learning of binary hash codes for efficient cross-modal retrieval. We…
Graph-wise Common Latent Factor Extraction for Unsupervised Graph Representation Learning
Thilini Cooray, Ngai-Man Cheung
Unsupervised graph-level representation learning plays a crucial role in a variety of tasks such as molecular property prediction and community analysis, especially when data annot…
Towards A Conceptually Simple Defensive Approach for Few-shot classifiers Against Adversarial Support Samples
Yi Xiang Marcus Tan, Penny Chong, Jiamei Sun +3
Few-shot classifiers have been shown to exhibit promising results in use cases where user-provided labels are scarce. These models are able to learn to predict novel classes simply…
Detection of Adversarial Supports in Few-shot Classifiers Using Self-Similarity and Filtering
Yi Xiang Marcus Tan, Penny Chong, Jiamei Sun +3
Few-shot classifiers excel under limited training samples, making them useful in applications with sparsely user-provided labels. Their unique relative prediction setup offers oppo…
Toward Scalable and Unified Example-based Explanation and Outlier Detection
Penny Chong, Ngai-Man Cheung, Yuval Elovici +1
When neural networks are employed for high-stakes decision-making, it is desirable that they provide explanations for their prediction in order for us to understand the features th…