24 citations · 81 across the 24 of their papers we have counts for
15 papers · 1 filter
Seeing Through the Weights: Privacy Leakage in Scene Coordinate Regression
Oleksii Nasypanyi, Jaemin Cho, Utku Ozbulak +2
Scene Coordinate Regression (SCR) methods are increasingly adopted for visual localization. In these approaches, the scene is implicitly encoded within a neural network that regres…
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…
Towards Affordable Tumor Segmentation and Visualization for 3D Breast MRI Using SAM2
Solha Kang, Eugene Kim, Joris Vankerschaver +1
Breast MRI provides high-resolution volumetric imaging critical for tumor assessment and treatment planning, yet manual interpretation of 3D scans remains labor-intensive and subje…
Evaluating Visual Explanations of Attention Maps for Transformer-based Medical Imaging
Minjae Chung, Jong Bum Won, Ganghyun Kim +2
Although Vision Transformers (ViTs) have recently demonstrated superior performance in medical imaging problems, they face explainability issues similar to previous architectures s…
One Patient's Annotation is Another One's Initialization: Towards Zero-Shot Surgical Video Segmentation with Cross-Patient Initialization
Seyed Amir Mousavi, Utku Ozbulak, Francesca Tozzi +4
Video object segmentation is an emerging technology that is well-suited for real-time surgical video segmentation, offering valuable clinical assistance in the operating room by en…
Revisiting the Evaluation Bias Introduced by Frame Sampling Strategies in Surgical Video Segmentation Using SAM2
Utku Ozbulak, Seyed Amir Mousavi, Francesca Tozzi +4
Real-time video segmentation is a promising opportunity for AI-assisted surgery, offering intraoperative guidance by identifying tools and anatomical structures. Despite growing in…
Color Flow Imaging Microscopy Improves Identification of Stress Sources of Protein Aggregates in Biopharmaceuticals
Michaela Cohrs, Shiwoo Koak, Yejin Lee +4
Protein-based therapeutics play a pivotal role in modern medicine targeting various diseases. Despite their therapeutic importance, these products can aggregate and form subvisible…
Identifying Critical Tokens for Accurate Predictions in Transformer-based Medical Imaging Models
Solha Kang, Joris Vankerschaver, Utku Ozbulak
With the advancements in self-supervised learning (SSL), transformer-based computer vision models have recently demonstrated superior results compared to convolutional neural netwo…
Self-supervised Benchmark Lottery on ImageNet: Do Marginal Improvements Translate to Improvements on Similar Datasets?
Utku Ozbulak, Esla Timothy Anzaku, Solha Kang +2
Machine learning (ML) research strongly relies on benchmarks in order to determine the relative effectiveness of newly proposed models. Recently, a number of prominent research eff…
Know Your Self-supervised Learning: A Survey on Image-based Generative and Discriminative Training
Utku Ozbulak, Hyun Jung Lee, Beril Boga +5
Although supervised learning has been highly successful in improving the state-of-the-art in the domain of image-based computer vision in the past, the margin of improvement has di…
Evaluating Adversarial Attacks on ImageNet: A Reality Check on Misclassification Classes
Utku Ozbulak, Maura Pintor, Arnout Van Messem +1
Although ImageNet was initially proposed as a dataset for performance benchmarking in the domain of computer vision, it also enabled a variety of other research efforts. Adversaria…
Selection of Source Images Heavily Influences the Effectiveness of Adversarial Attacks
Utku Ozbulak, Esla Timothy Anzaku, Wesley De Neve +1
Although the adoption rate of deep neural networks (DNNs) has tremendously increased in recent years, a solution for their vulnerability against adversarial examples has not yet be…
Investigating the significance of adversarial attacks and their relation to interpretability for radar-based human activity recognition systems
Utku Ozbulak, Baptist Vandersmissen, Azarakhsh Jalalvand +3
Given their substantial success in addressing a wide range of computer vision challenges, Convolutional Neural Networks (CNNs) are increasingly being used in smart home application…