Ioana Giurgiu

Title

Senior Research Scientist and Manager

Ioana Giurgiu

Bio

I joined IBM in 2012 and am currently a Senior Research Scientist of the AI Automation group, where I am leading the anomaly detection for visual inspection effort. My interests mainly revolve around explainable and robust AI (in particular deep learning models), unsupervized learning, as well as predictive analytics.

I graduated with a Ph.D. in Computer Science from the Swiss Federal Institute of Technology (ETHZ) in September 2012. Prior to that, in 2008 I got my Eng. degree in Computer Science from the Technical University of Cluj-Napoca, Romania.

Publications

Probabilistic feature matching for fast scalable visual prompting
- - Thomas Frick
  - Cezary Skura
  - et al.
- 2024
- IJCAI 2024
AI for Bridge Inspection with IBM Inspecto
- - Cristiano Malossi
  - Roy Assaf
  - et al.
- 2024
- IABMAS 2024
Interactive Image Segmentation Guided by Visual Prompting
- - Thomas Frick
  - Cezary Skura
  - et al.
- 2024
- CVPR 2024
MC Layer Normalization for calibrated uncertainty in Deep Learning
- - Thomas Frick
  - Diego Antognini
  - et al.
- 2024
- TMLR
Towards Workﬂows for the Use of AI Foundation Models in Visual Inspection Applications
- - Mattia Rigotti
  - Diego Antognini
  - et al.
- 2023
- EUROSTRUCT 2023
Model-Assisted Labeling via Explainability for Visual Inspection of Civil Infrastructures
- - Klara Janouskova
  - Mattia Rigotti
  - et al.
- 2022
- ECCV 2022
Active Learning for Imbalanced Civil Infrastructure Data
- - Thomas Frick
  - Diego Antognini
  - et al.
- 2022
- ECCV 2022
Attention-based Interpretability with Concept Transformers
- - Mattia Rigotti
  - Christoph Miksovic Czasch
  - et al.
- 2022
- ICLR 2022
CCA: An ML Pipeline for Cloud Anomaly Troubleshooting
- - Lili Georgieva
  - Ioana Giurgiu
  - et al.
- 2022
- AAAI 2022

Patents

- 10 Nov 2024
- JP
- 7586613
Performance Event Troubleshooting System
- 12 Jun 2023
- US
- 11675799
Anomaly Detection System
- 07 Feb 2022
- US
- 11243833
Performance Event Troubleshooting System
- 10 Sep 2018
- US
- 10074055
Assisting Database Management
- 01 Aug 2016
- US
- 9406023
System Recommendations Based On Incident Analysis

Projects

Visual Prompting

Using AI to build computer vision models within minutes, through quick intuitive prompts, and with just a few images

Inspecto – Large Vision Model Inspection Service

Increasing speed and quality of enterprise visual inspection, leveraging AI and domain-specific Large Vision Models

View more projects

View more projects

Top collaborators

MR

Mattia Rigotti

Mattia Rigotti

Senior Research Scientist

CM

Cristiano Malossi

Cristiano Malossi

Principal Research Scientist and Manager

TF

Thomas Frick

Thomas Frick

Pre-Doctoral Researcher

FS

Florian Scheidegger

Florian Scheidegger

Research Scientist