104 citations
Counting papers with at most 25 authors, so collaboration author lists do not stand in for the people here.
12 papers
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…
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…
Exploring Patient Data Requirements in Training Effective AI Models for MRI-based Breast Cancer Classification
Solha Kang, Wesley De Neve, Francois Rameau +1
The past decade has witnessed a substantial increase in the number of startups and companies offering AI-based solutions for clinical decision support in medical institutions. Howe…
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…
On a Mixed Arithmetic-Mean, Geometric-Mean, Harmonic-Mean Inequality
Kyumin Nam
A mixed arithmetic-mean, geometric-mean inequality was conjectured by F. Holland and proved by K. Kedlaya. In this note, we prove a mixed arithmetic-mean, harmonic-mean inequality…
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…
Perturbation Analysis of Gradient-based Adversarial Attacks
Utku Ozbulak, Manvel Gasparyan, Wesley De Neve +1
After the discovery of adversarial examples and their adverse effects on deep learning models, many studies focused on finding more diverse methods to generate these carefully craf…
Restricted Boltzmann Machines for Quantum States with Nonabelian or Anyonic Symmetries
Tom Vieijra, Corneel Casert, Jannes Nys +4
Although artificial neural networks have recently been proven to provide a promising new framework for constructing quantum many-body wave functions, the parameterization of a quan…
Dual Rectified Linear Units (DReLUs): A Replacement for Tanh Activation Functions in Quasi-Recurrent Neural Networks
Fréderic Godin, Jonas Degrave, Joni Dambre +1
In this paper, we introduce a novel type of Rectified Linear Unit (ReLU), called a Dual Rectified Linear Unit (DReLU). A DReLU, which comes with an unbounded positive and negative…
Complex and detailed balancing of chemical reaction networks revisited
Arjan van der Schaft, Shodhan Rao, Bayu Jayawardhana
The characterization of the notions of complex and detailed balancing for mass action kinetics chemical reaction networks is revisited from the perspective of algebraic graph theor…