26 citations · 92 across the 41 of their papers we have counts for
44 papers
You Are the Trigger: Speaker-Activated Backdoors
Nataša Krčo, Euodia Dodd, Peter Romov +1
Speech models are increasingly used as an interface to AI systems, from transcription tools to voice agents. Existing audio backdoors require an attacker to introduce triggers at i…
SABRE: A Multi-Agent Approach for Selecting Out-of-Distribution Detectors Under a Budget
Mary Wisell, Salimeh Sekeh
Post-hoc out-of-distribution (OOD) detection for vision-language models assumes that a detector chosen on a benchmark stays reliable once deployed. We show this fails across domain…
C-GAP: Class-Aware and Online Prompting Improves Vision-Language Models on Imbalanced Classes
Francis Fernandez, Arash Jahangiri, Salimeh Sekeh
Safety-critical perception systems must reliably detect rare object classes within small label spaces, a setting that long-tailed detection methods, designed for hundreds of classe…
Cross-Contextual Vision-Language Adaptation with LoRA for Personalized Severe Adverse Event Detection in Clinical Wound Monitoring
Aditi Naiknaware, Jian Sun, Aminreza Khandan +4
Wound monitoring is a critical yet underserved clinical challenge, where timely identification of severe adverse events (SAEs) such as infection, tissue deterioration, and delayed…
Theoretical Grounding of Out-Of-Distribution Detection With Reinforcement Learning Optimizer
Salimeh Sekeh, Xin Zhang
Out-of-distribution (OOD) detection in dynamic open-world environments requires a model to continually adapt to evolving data distributions while generalizing to covariate-shifted…
GRASP: Gradient-Aligned Sequential Parameter Transfer for Memory-Efficient Multi-Source Learning
Mary Isabelle Wisell, Nicholas Jacobs, Aayush Manandhar +1
Multi-source transfer learning faces a fundamental scalability bottleneck: existing approaches require either loading all K source models into memory simultaneously during paramete…
Understanding Cross-Modal Contributions in Continual Vision-Language Models: A Theoretical Perspective
Salimeh Sekeh, Mary Wisell
Continual vision-language models are commonly addressed through sequential fine-tuning; however, although this paradigm enables adaptation to new environments (tasks), it inherentl…
T-QPM: Enabling Temporal Out-Of-Distribution Detection and Domain Generalization for Vision-Language Models in Open-World
Aditi Naiknaware, Salimeh Sekeh
Out-of-distribution (OOD) detection remains a critical challenge in open-world learning, where models must adapt to evolving data distributions. While recent vision-language models…
Temp-SCONE: A Novel Out-of-Distribution Detection and Domain Generalization Framework for Wild Data with Temporal Shift
Aditi Naiknaware, Sanchit Singh, Hajar Homayouni +1
Open-world learning (OWL) requires models that can adapt to evolving environments while reliably detecting out-of-distribution (OOD) inputs. Existing approaches, such as SCONE, ach…
Weather-Aware Object Detection Transformer for Domain Adaptation
Soheil Gharatappeh, Salimeh Sekeh, Vikas Dhiman
RT-DETRs have shown strong performance across various computer vision tasks but are known to degrade under challenging weather conditions such as fog. In this work, we investigate…
Information Consistent Pruning: How to Efficiently Search for Sparse Networks?
Soheil Gharatappeh, Salimeh Yasaei Sekeh
Iterative magnitude pruning methods (IMPs), proven to be successful in reducing the number of insignificant nodes in over-parameterized deep neural networks (DNNs), have been getti…
Ghost-Connect Net: A Generalization-Enhanced Guidance For Sparse Deep Networks Under Distribution Shifts
Mary Isabelle Wisell, Salimeh Yasaei Sekeh
Sparse deep neural networks (DNNs) excel in real-world applications like robotics and computer vision, by reducing computational demands that hinder usability. However, recent stud…
Robust Subgraph Learning by Monitoring Early Training Representations
Sepideh Neshatfar, Salimeh Yasaei Sekeh
Graph neural networks (GNNs) have attracted significant attention for their outstanding performance in graph learning and node classification tasks. However, their vulnerability to…
FogGuard: guarding YOLO against fog using perceptual loss
Soheil Gharatappeh, Sepideh Neshatfar, Salimeh Yasaei Sekeh +1
In this paper, we present FogGuard, a novel fog-aware object detection network designed to address the challenges posed by foggy weather conditions. Autonomous driving systems heav…
Investigating the Impact of Weight Sharing Decisions on Knowledge Transfer in Continual Learning
Josh Andle, Ali Payani, Salimeh Yasaei-Sekeh
Continual Learning (CL) has generated attention as a method of avoiding Catastrophic Forgetting (CF) in the sequential training of neural networks, improving network efficiency and…
A Theoretical Perspective on Subnetwork Contributions to Adversarial Robustness
Jovon Craig, Josh Andle, Theodore S. Nowak +1
The robustness of deep neural networks (DNNs) against adversarial attacks has been studied extensively in hopes of both better understanding how deep learning models converge and i…
Promise and Limitations of Supervised Optimal Transport-Based Graph Summarization via Information Theoretic Measures
Sepideh Neshatfar, Abram Magner, Salimeh Yasaei Sekeh
Graph summarization is the problem of producing smaller graph representations of an input graph dataset, in such a way that the smaller compressed graphs capture relevant structura…
Improving Hyperspectral Adversarial Robustness Under Multiple Attacks
Nicholas Soucy, Salimeh Yasaei Sekeh
Semantic segmentation models classifying hyperspectral images (HSI) are vulnerable to adversarial examples. Traditional approaches to adversarial robustness focus on training or re…
Theoretical Understanding of the Information Flow on Continual Learning Performance
Josh Andle, Salimeh Yasaei Sekeh
Continual learning (CL) is a setting in which an agent has to learn from an incoming stream of data sequentially. CL performance evaluates the model's ability to continually learn…
Q-TART: Quickly Training for Adversarial Robustness and in-Transferability
Madan Ravi Ganesh, Salimeh Yasaei Sekeh, Jason J. Corso
Raw deep neural network (DNN) performance is not enough; in real-world settings, computational load, training efficiency and adversarial security are just as or even more important…
The Stanford Drone Dataset is More Complex than We Think: An Analysis of Key Characteristics
Joshua Andle, Nicholas Soucy, Simon Socolow +1
Several datasets exist which contain annotated information of individuals' trajectories. Such datasets are vital for many real-world applications, including trajectory prediction a…
CEU-Net: Ensemble Semantic Segmentation of Hyperspectral Images Using Clustering
Nicholas Soucy, Salimeh Yasaei Sekeh
Most semantic segmentation approaches of Hyperspectral images (HSIs) use and require preprocessing steps in the form of patching to accurately classify diversified land cover in re…
Adaptive County Level COVID-19 Forecast Models: Analysis and Improvement
Stewart W Doe, Tyler Russell Seekins, David Fitzpatrick +2
Accurately forecasting county level COVID-19 confirmed cases is crucial to optimizing medical resources. Forecasting emerging outbreaks pose a particular challenge because many exi…
Slimming Neural Networks using Adaptive Connectivity Scores
Madan Ravi Ganesh, Dawsin Blanchard, Jason J. Corso +1
In general, deep neural network (DNN) pruning methods fall into two categories: 1) Weight-based deterministic constraints, and 2) Probabilistic frameworks. While each approach has…