209 citations · 216 across the 28 of their papers we have counts for
30 papers
CACFG: Curvature-Aware Classifier-Free Guidance and Optimal Control
Max Collins, Dasith de Silva Edirimuni, Jordan Vice +2
Diffusion models generate samples by learning to reverse a fixed corruption process, and classifier-free guidance (CFG) is the standard mechanism for conditioning this process on a…
Mitigating Memorization in Text-to-Image Diffusion via Region-Aware Prompt Augmentation and Multimodal Copy Detection
Yunzhuo Chen, Jordan Vice, Naveed Akhtar +2
State-of-the-art text-to-image diffusion models can produce impressive visuals but may memorize and reproduce training images, creating copyright and privacy risks. Existing prompt…
Attribution-Guided Model Rectification of Unreliable Neural Network Behaviors
Peiyu Yang, Naveed Akhtar, Jiantong Jiang +1
The performance of neural network models deteriorates due to their unreliable behavior on non-robust features of corrupted samples. Owing to their opaque nature, rectifying models…
Implicit Neural Representation-Based Continuous Single Image Super-Resolution: An Empirical Benchmark
Tayyab Nasir, Daochang Liu, Ajmal Mian
Implicit neural representation (INR) has become the standard approach for arbitrary-scale image super-resolution (ASSR). However, no systematic empirical study has examined the eff…
DRBD-Mamba for Robust and Efficient Brain Tumor Segmentation with Analytical Insights
Danish Ali, Ajmal Mian, Naveed Akhtar +1
Accurate brain tumor segmentation is significant for clinical diagnosis and treatment but remains challenging due to tumor heterogeneity. Mamba-based State Space Models have demons…
CymbaDiff: Structured Spatial Diffusion for Sketch-based 3D Semantic Urban Scene Generation
Li Liang, Bo Miao, Xinyu Wang +3
Outdoor 3D semantic scene generation produces realistic and semantically rich environments for applications such as urban simulation and autonomous driving. However, advances in th…
On the Reliability of Vision-Language Models Under Adversarial Frequency-Domain Perturbations
Jordan Vice, Naveed Akhtar, Yansong Gao +2
Vision-Language Models (VLMs) are increasingly used as perceptual modules for visual content reasoning, including through captioning and DeepFake detection. In this work, we expose…
Multistream Network for LiDAR and Camera-based 3D Object Detection in Outdoor Scenes
Muhammad Ibrahim, Naveed Akhtar, Haitian Wang +2
Fusion of LiDAR and RGB data has the potential to enhance outdoor 3D object detection accuracy. To address real-world challenges in outdoor 3D object detection, fusion of LiDAR and…
NatADiff: Adversarial Boundary Guidance for Natural Adversarial Diffusion
Max Collins, Jordan Vice, Tim French +1
Adversarial samples exploit irregularities in the manifold `learned' by deep learning models to cause misclassifications. The study of these adversarial samples provides insight in…
Deeper Diffusion Models Amplify Bias
Shahin Hakemi, Naveed Akhtar, Ghulam Mubashar Hassan +1
Despite the remarkable performance of generative Diffusion Models (DMs), their internal working is still not well understood, which is potentially problematic. This paper focuses o…
On Transfer-based Universal Attacks in Pure Black-box Setting
Mohammad A. A. K. Jalwana, Naveed Akhtar, Ajmal Mian +2
Despite their impressive performance, deep visual models are susceptible to transferable black-box adversarial attacks. Principally, these attacks craft perturbations in a target m…
Exploring Bias in over 100 Text-to-Image Generative Models
Jordan Vice, Naveed Akhtar, Richard Hartley +1
We investigate bias trends in text-to-image generative models over time, focusing on the increasing availability of models through open platforms like Hugging Face. While these pla…
Image Watermarking of Generative Diffusion Models
Yunzhuo Chen, Jordan Vice, Naveed Akhtar +2
Embedding watermarks into the output of generative models is essential for establishing copyright and verifiable ownership over the generated content. Emerging diffusion model wate…
Deepfake Detection with Spatio-Temporal Consistency and Attention
Yunzhuo Chen, Naveed Akhtar, Nur Al Hasan Haldar +1
Deepfake videos are causing growing concerns among communities due to their ever-increasing realism. Naturally, automated detection of forged Deepfake videos is attracting a propor…
Dynamic watermarks in images generated by diffusion models
Yunzhuo Chen, Naveed Akhtar, Nur Al Hasan Haldar +1
High-fidelity text-to-image diffusion models have revolutionized visual content generation, but their widespread use raises significant ethical concerns, including intellectual pro…
Skip Mamba Diffusion for Monocular 3D Semantic Scene Completion
Li Liang, Naveed Akhtar, Jordan Vice +2
3D semantic scene completion is critical for multiple downstream tasks in autonomous systems. It estimates missing geometric and semantic information in the acquired scene data. Du…
Single-weight Model Editing for Post-hoc Spurious Correlation Neutralization
Shahin Hakemi, Naveed Akhtar, Ghulam Mubashar Hassan +1
Neural network training tends to exploit the simplest features as shortcuts to greedily minimize training loss. However, some of these features might be spuriously correlated with…
Safety Without Semantic Disruptions: Editing-free Safe Image Generation via Context-preserving Dual Latent Reconstruction
Jordan Vice, Naveed Akhtar, Mubarak Shah +2
Training multimodal generative models on large, uncurated datasets can result in users being exposed to harmful, unsafe and controversial or culturally-inappropriate outputs. While…
On the Fairness, Diversity and Reliability of Text-to-Image Generative Models
Jordan Vice, Naveed Akhtar, Leonid Sigal +2
The rapid proliferation of multimodal generative models has sparked critical discussions on their reliability, fairness and potential for misuse. While text-to-image models excel a…
Artificial intelligence techniques in inherited retinal diseases: A review
Han Trinh, Jordan Vice, Jason Charng +4
Inherited retinal diseases (IRDs) are a diverse group of genetic disorders that lead to progressive vision loss and are a major cause of blindness in working-age adults. The comple…
FastBO: Fast HPO and NAS with Adaptive Fidelity Identification
Jiantong Jiang, Ajmal Mian
Hyperparameter optimization (HPO) and neural architecture search (NAS) are powerful in attaining state-of-the-art machine learning models, with Bayesian optimization (BO) standing…
Regulating Model Reliance on Non-Robust Features by Smoothing Input Marginal Density
Peiyu Yang, Naveed Akhtar, Mubarak Shah +1
Trustworthy machine learning necessitates meticulous regulation of model reliance on non-robust features. We propose a framework to delineate and regulate such features by attribut…
Fast-PGM: Fast Probabilistic Graphical Model Learning and Inference
Jiantong Jiang, Zeyi Wen, Peiyu Yang +2
Probabilistic graphical models (PGMs) serve as a powerful framework for modeling complex systems with uncertainty and extracting valuable insights from data. However, users face ch…
A Backdoor-based Explainable AI Benchmark for High Fidelity Evaluation of Attributions
Peiyu Yang, Naveed Akhtar, Jiantong Jiang +1
Attribution methods compute importance scores for input features to explain model predictions. However, assessing the faithfulness of these methods remains challenging due to the a…