CV

Klára Janoušková

Prague, Czech Republic · klara.janou@gmail.com · LinkedIn · GitHub · Google Scholar · Bluesky

Download PDF

Research Interests

Computer vision and machine learning, with a focus on vision-language models (VLMs) and multimodal large language models (MLLMs) for image recognition, efficient VLM adaptation, and context-aware robust object recognition. Additional interests include fine-grained visual classification, test-time adaptation, zero-shot segmentation, and learning with limited supervision.

Education

Ph.D. in Computer Vision and Machine Learning — Czech Technical University in Prague (CTU)
2023 – present
Prague, Czech Republic
M.Sc. in Computer Science — Czech Technical University in Prague (CTU)
2021 – 2023
Prague, Czech Republic
  • Thesis: Test-Time Adaptation for Segmentation — link
B.Sc. in Open Informatics — Czech Technical University in Prague (CTU)
2017 – 2021
Prague, Czech Republic
  • Thesis: Scene Text Detection and Recognition — link · Dean's Award

Research Experience

PhD Researcher — Czech Technical University in Prague
2023 – present
Prague, Czech Republic
  • Research on zero-shot segmentation, recognition robustness, VLM adaptation, and fine-grained classification of fungi.
  • Co-supervision of BSc, MSc, and high-school students.
Research Intern — Technion — Israel Institute of Technology
2022 – 2023
Haifa, Israel
  • Selected via the Czech-Israeli Innovation Internship (CI3) program.
  • Supervised by Chaim Baskin and Alex Bronstein.
  • Developed single-image test-time adaptation for segmentation; published at TMLR 2024.
Research Intern — IBM Research Zurich
2022
Zürich, Switzerland
  • Selected via IBM Great Minds fellowship.
  • Supervised by Mattia Rigotti, Ioana Giurgiu, and Cristiano Malossi.
  • Model-assisted labelling and AI foundation models for visual inspection of civil infrastructure.
  • Best Paper Award at ECCV 2022 Workshop on CV for Civil and Infrastructure Engineering.
Research Intern — Computer Vision Center (CVC) at UAB
2019 – 2020
Barcelona, Spain

Teaching

Teaching Assistant — Czech Technical University in Prague
2023 – present
Prague, Czech Republic
  • Labs for the Machine Learning and Pattern Recognition course.
  • Co-supervision of BSc, MSc, and high-school students.

Patents

  • Klára Janoušková, Ioana Giurgiu, Mattia Rigotti, Cristiano Malossi. Generating Strong Labels for Examples Labelled with Weak Labels. US Patent 12,406,478. Granted 2025.

Publications

Full list also on Google Scholar.

  1. Matej Suchanek, Klara Janouskova, Ondrej Vasatko, Jiri Matas. “Koo-Fu CLIP: Closed-Form Adaptation of Vision-Language Models via Fukunaga-Koontz Linear Discriminant Analysis.” arXiv preprint, 2026. [link]
  2. Klara Janouskova, Cristian Gavrus, Jiri Matas. “Robust Context-Aware Object Recognition.” arXiv preprint, 2025. [link]
  3. Illia Volkov, Nikita Kisel, Klara Janouskova, Jiri Matas. “Image Recognition with Vision and Language Embeddings of VLMs.” British Machine Vision Conference (BMVC), 2025. [link]
  4. Nikita Kisel, Illia Volkov, Klara Janouskova, Jiri Matas. “Multimodal LLMs as Image Classifiers.” IEEE/CVF CVPR Findings, 2026. [link]
  5. Alen Adamyan, Tomáš Čížek, Matej Straka, Klara Janouskova, Martin Schmid. “SAM2RL: Towards Reinforcement Learning Memory Control in Segment Anything Model 2.” RL4RS @ RLC, 2025. [link]
  6. Klara Janouskova, Jiri Matas, Lukas Picek. “Overview of FungiCLEF 2025: Few-Shot Classification with Rare Fungi Species.” Working Notes of CLEF, 2025.
  7. Lukas Picek, Stefan Kahl, Hervé Goëau, et al. “Overview of LifeCLEF 2025.” Working Notes of CLEF, 2025.
  8. Alexis Joly, Lukas Picek, Stefan Kahl, et al. “LifeCLEF 2025 Teaser.” European Conference on Information Retrieval (ECIR), 2025.
  9. Nikita Kisel, Illia Volkov, Katerina Hanzelkova, Klara Janouskova, Jiri Matas. “Flaws of ImageNet, Computer Vision's Favourite Dataset.” ICLR 2025 Blog Posts Track, 2025. [link]
  10. Lukas Picek, Klara Janouskova, Vojtech Cermak, Jiri Matas. “FungiTastic: A Multi-modal Dataset and Benchmark for Image Categorization.” FGVC @ CVPR, 2025. [link]
  11. Klara Janouskova, Tamir Shor, Chaim Baskin, Jiri Matas. “Single Image Test-Time Adaptation for Segmentation.” Transactions on Machine Learning Research (TMLR), 2024. [link]
  12. Mattia Rigotti, Diego Antognini, Roy Assaf, Kagan Bakirci, Thomas Frick, Ioana Giurgiu, Klára Janoušková, Filip Janicki, Husam Jubran, Cristiano Malossi, Alexandru Meterez, Florian Scheidegger. “Towards Workflows for the Use of AI Foundation Models in Visual Inspection Applications.” EUROSTRUCT, 2023. [link]
  13. Klara Janouskova, Mattia Rigotti, Ioana Giurgiu, Cristiano Malossi. “Model-Assisted Labeling via Explainability for Visual Inspection of Civil Infrastructures.” ECCV 2022 Workshop on CV for Civil and Infrastructure Engineering, 2022. Best Paper Award. [link]
  14. Klára Janoušková, Jiri Matas, Lluis Gomez, Dimosthenis Karatzas. “Text Recognition — Real World Data and Where to Find Them.” International Conference on Pattern Recognition (ICPR), 2021. [link]

Skills

Languages
Python, Bash, LaTeX
Frameworks
PyTorch, Hugging Face Transformers, OpenCV
Areas
Computer Vision, Machine Learning, Zero-Shot Segmentation, Test-Time Adaptation, Fine-Grained Classification

Awards & Honours

  • Top Reviewer — NeurIPS 2024
  • Josef Hlavka Award — The Foundation of Josef, Marie and Zdeňka Hlávka, 2022
    Awarded to outstanding students and graduates (oldest Czech foundation supporting science and culture).
  • Best Paper Award — ECCV 2022, Workshop on Computer Vision for Civil and Infrastructure Engineering
  • Dean's Award for Outstanding Bachelor's Thesis — Czech Technical University, 2020
  • 100th Percentile, SCIO National Comparative Exams in Mathematics — 2017
    Best result in the cohort; used as an admission criterion at many Czech universities.
  • Open Informatics Scholarship for Talented Girls — 2017
    Awarded to top-scoring students in the NCE in Mathematics.

Grants & Funding

  • Toyota Motors Europe Research Grant — €100,000 (2025–2026)
    One-year research project on efficient vision-language models.

Professional Service

Reviewing
NeurIPS (Top Reviewer 2024), CVPR, ECCV, ICCV, BMVC