Utku Ozbulak

Orcid: 0000-0003-3084-6034

According to our database1, Utku Ozbulak authored at least 29 papers between 2018 and 2025.

Collaborative distances:
  • Dijkstra number2 of four.
  • Erdős number3 of five.

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

Online presence:

On csauthors.net:

Bibliography

2025
SpurBreast: A Curated Dataset for Investigating Spurious Correlations in Real-world Breast MRI Classification.
CoRR, October, 2025

When Tracking Fails: Analyzing Failure Modes of SAM2 for Point-Based Tracking in Surgical Videos.
CoRR, October, 2025

Detecting Regional Spurious Correlations in Vision Transformers via Token Discarding.
CoRR, September, 2025

Improved Sub-Visible Particle Classification in Flow Imaging Microscopy via Generative AI-Based Image Synthesis.
CoRR, August, 2025

One Patient's Annotation is Another One's Initialization: Towards Zero-Shot Surgical Video Segmentation with Cross-Patient Initialization.
CoRR, March, 2025

Less is More? Revisiting the Importance of Frame Rate in Real-Time Zero-Shot Surgical Video Segmentation.
CoRR, February, 2025

SpurBreast: A Curated Dataset for Investigating Spurious Correlations in Real-World Breast MRI Classification.
Proceedings of the Medical Image Computing and Computer Assisted Intervention - MICCAI 2025, 2025

Revisiting the Evaluation Bias Introduced by Frame Sampling Strategies in Surgical Video Segmentation Using SAM2.
Proceedings of the Fairness of AI in Medical Imaging - Third International Workshop, 2025

Balancing Redundancy and Diversity: An In-Depth Analysis of Active Learning for Laparoscopic Video Segmentation.
Proceedings of the Data Engineering in Medical Imaging - Third MICCAI Workshop, 2025

Towards Affordable Tumor Segmentation and Visualization for 3D Breast MRI Using SAM2.
Proceedings of the Artificial Intelligence and Imaging for Diagnostic and Treatment Challenges in Breast Care, 2025

2024
Assessing the reliability of point mutation as data augmentation for deep learning with genomic data.
BMC Bioinform., December, 2024

Identifying Critical Tokens for Accurate Predictions in Transformer-Based Medical Imaging Models.
Proceedings of the Machine Learning in Medical Imaging - 15th International Workshop, 2024

Exploring Patient Data Requirements in Training Effective AI Models for MRI-Based Breast Cancer Classification.
Proceedings of the Artificial Intelligence and Imaging for Diagnostic and Treatment Challenges in Breast Care, 2024

Color Flow Imaging Microscopy Improves Identification of Stress Sources of Protein Aggregates in Biopharmaceuticals.
Proceedings of the Medical Optical Imaging and Virtual Microscopy Image Analysis, 2024

Evaluating Visual Explanations of Attention Maps for Transformer-Based Medical Imaging.
Proceedings of the Medical Image Computing and Computer Assisted Intervention - MICCAI 2024 Workshops, 2024

Self-supervised Benchmark Lottery on ImageNet: Do Marginal Improvements Translate to Improvements on Similar Datasets?
Proceedings of the International Joint Conference on Neural Networks, 2024

2023
Know Your Self-supervised Learning: A Survey on Image-based Generative and Discriminative Training.
Trans. Mach. Learn. Res., 2023

BRCA Gene Mutations in dbSNP: A Visual Exploration of Genetic Variants.
CoRR, 2023

2022
Utilizing Mutations to Evaluate Interpretability of Neural Networks on Genomic Data.
CoRR, 2022

Exact Feature Collisions in Neural Networks.
CoRR, 2022

2021
Investigating the significance of adversarial attacks and their relation to interpretability for radar-based human activity recognition systems.
Comput. Vis. Image Underst., 2021

Evaluating Adversarial Attacks on ImageNet: A Reality Check on Misclassification Classes.
CoRR, 2021

Selection of Source Images Heavily Influences the Effectiveness of Adversarial Attacks.
Proceedings of the 32nd British Machine Vision Conference 2021, 2021

2020
Perturbation analysis of gradient-based adversarial attacks.
Pattern Recognit. Lett., 2020

Regional Image Perturbation Reduces L<sub>p</sub> Norms of Adversarial Examples While Maintaining Model-to-model Transferability.
CoRR, 2020

Automatic Detection of Trypanosomosis in Thick Blood Smears Using Image Pre-processing and Deep Learning.
Proceedings of the Intelligent Human Computer Interaction - 12th International Conference, 2020

2019
Impact of Adversarial Examples on Deep Learning Models for Biomedical Image Segmentation.
Proceedings of the Medical Image Computing and Computer Assisted Intervention - MICCAI 2019, 2019

Not All Adversarial Examples Require a Complex Defense: Identifying Over-optimized Adversarial Examples with IQR-based Logit Thresholding.
Proceedings of the International Joint Conference on Neural Networks, 2019

2018
How the Softmax Output is Misleading for Evaluating the Strength of Adversarial Examples.
CoRR, 2018


  Loading...