5 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…
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…
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…