14 papers
FedRef: Bayesian Fine-Tuning using a Reference Model to Mitigate Catastrophic Forgetting for Heterogeneous Federated Learning
Taehwan Yoon, Bongjun Choi, Wesley De Neve
Federated learning (FL) enables collaborative model training across distributed clients while preserving data privacy. However, data and system heterogeneity often cause catastroph…
SpurBreast: A Curated Dataset for Investigating Spurious Correlations in Real-world Breast MRI Classification
Jong Bum Won, Wesley De Neve, Joris Vankerschaver +1
Deep neural networks (DNNs) have demonstrated remarkable success in medical imaging, yet their real-world deployment remains challenging due to spurious correlations, where models…
When Tracking Fails: Analyzing Failure Modes of SAM2 for Point-Based Tracking in Surgical Videos
Woowon Jang, Jiwon Im, Juseung Choi +3
Video object segmentation (VOS) models such as SAM2 offer promising zero-shot tracking capabilities for surgical videos using minimal user input. Among the available input types, p…
Token-Based Detection of Spurious Correlations in Vision Transformers
Solha Kang, Esla Timothy Anzaku, Wesley De Neve +4
Due to their powerful feature association capabilities, neural network-based computer vision models have the ability to detect and exploit unintended patterns within the data, pote…
Improved Sub-Visible Particle Classification in Flow Imaging Microscopy via Generative AI-Based Image Synthesis
Utku Ozbulak, Michaela Cohrs, Hristo L. Svilenov +2
Sub-visible particle analysis using flow imaging microscopy combined with deep learning has proven effective in identifying particle types, enabling the distinction of harmless com…
Toward Using Machine Learning as a Shape Quality Metric for Liver Point Cloud Generation
Khoa Tuan Nguyen, Gaeun Oh, Ho-min Park +5
While 3D medical shape generative models such as diffusion models have shown promise in synthesizing diverse and anatomically plausible structures, the absence of ground truth make…