Please join us on Friday, January 30, 2026, from 12:30 PM to 1:30 PM for the in-person ISP Forum in SENSQ 5317. We will be featuring Zhiwei Gong,  Yaohan Ding, and Cagri Gungor.  Lunch and refreshments will be provided, starting at noon.

Zhiwei Gong Presentation Information

Title: An Unsupervised Domain Adaptation Method to Enhance Diagnostic Model Resilience on Heterogeneous Medical Imaging Data

Abstract: Deep learning models trained on a single dataset often experience performance degradation when applied to external datasets due to data shifts. Data shifts undermine robustness, generalizability, and trustworthiness of clinical AI systems. In this study, we propose VIC-Adaptor, a novel unsupervised domain adaptation (UDA) method that enhances medical imaging diagnostic model’s generalizability on heterogeneous datasets and thus the resilience to data complexity in real-world medical applications. VIC-Adaptor introduces a new Variance-Invariance-Covariance Feature Alignment Loss (VICFAL), which promotes cross-domain feature alignment, preserves representational diversity, and minimizes redundancy without requiring labels of the data from the target domain during model training. We conducted experiments on two breast imaging datasets (i.e., contrast-enhanced mammography) with varying cohorts, each serving alternately as the source and target domain. Results showed that VIC-Adaptor consistently improves AUC values in the target domain, outperforming several compared existing UDA methods. Our proposed method can contribute to enhancing medical diagnostic model’s resilience to heterogeneous imaging datasets, generalizability across the data from different sources/institutions, and increase model users’ trust to AI model’s clinical utilities in real-world environments

Bio: Zhiwei Gong is a second-year PhD student in the Intelligent Systems Program at the University of Pittsburgh, advised by Dr. Shandong Wu. His research interests lie at the intersection of deep learning, medical image analysis, and agentic AI, with a primary focus on breast cancer applications.

Yaohan Ding Presentation Information

Title: Explanations Help: Leveraging Human Capabilities to Detect Cyberattacks on Automated Vehicles

Abstract: Existing defense strategies against cyberattacks on automated vehicles (AVs) often overlook the great potential of humans in detecting such attacks. To address this, we identified three types of human-detectable attacks targeting transportation infrastructure, AV perception modules, and AV execution modules. We proposed two types of displays: Alert and Alert plus Explanations (AlertExp), and conducted an online video survey study involving 260 participants to systematically evaluate the effectiveness of these displays across cyberattack types. Results showed that AV execution module attacks were the hardest to detect and understand, but AlertExp displays mitigated this difficulty. In contrast, AV perception module attacks were the easiest to detect, while infrastructure attacks resulted in the highest post-attack trust in the AV system. Although participants were prone to false alarms, AlertExp displays mitigated their negative impacts, whereas Alert displays performed worse than having no display. Overall, AlertExp displays are recommended to enhance human detection of cyberattacks.

Bio:  Yaohan Ding is a PhD candidate in the Intelligent Systems Program at the University of Pittsburgh. Her research focuses on enhancing human-autonomy interactions through human-centered designs.

Cagri Gungor Presentation Information

Title: Integrating Audio Narrations to Strengthen Domain Generalization in Multimodal First-Person Action Recognition

Abstract: First-person activity recognition is rapidly growing due to the widespread use of wearable cameras but faces challenges from domain shifts across different environments, such as varying objects or background scenes. We propose a multimodal framework that improves domain generalization by integrating motion, audio, and appearance features. Key contributions include analyzing the resilience of audio and motion features to domain shifts, using audio narrations for enhanced audio-text alignment, and applying consistency ratings between audio and visual narrations to optimize the impact of audio in recognition during training. Our approach achieves state-of-the-art performance on the ARGO1M dataset, effectively generalizing across unseen scenarios and locations.

Bio: Cagri Gungor is a Ph.D. Candidate in the Intelligent Systems Program at University of Pittsburgh. His research bridges the gap between visual perception and human understanding by harnessing complementary modalities such as audio, depth, motion, and touch to tackle visual uncertainty in computer vision.