|
Hello! I am an AI researcher. I focus on deep learning of self-supervised representations. My goal is to develop autonomous visual learners that can continuously improve by extracting their own supervision from dynamic visual data streams. I have worked at the Learning to Learn Lab, where I advanced techniques in self-supervised continual learning, enabling AI systems to autonomously adapt and improve without relying on external annotations. Before that, I obtained my PhD at the QUvA Lab , on deep vision under the guidance of Arnold Smeulders. Email | CV | Google Scholar | LinkedIn |
|
News
- 10/2024
- 07/2024
- 09/2023
- 04/2023
- 02/2023
- 11/2022
|
Learning to Learn Lab, Eindhoven University of Technology, Netherlands
2022-2023
Researcher |
|
QUvA Deep Vision Lab, University of Amsterdam, Netherlands
2017-2022
PhD Researcher |
|
Huawei Visual Search Lab, Helsinki, Finland
2021 March - 2022 January
Research Scientist Intern |
|
Université Laval Computer Vision Lab, Quebec, Canada
2015 March - 2015 October
Research Intern |
Research
|
Fangqin Zhou, Mert Kilickaya, Joaquin Vanschoren Ran Piao ECCV 2024 arXiv / Github We present HyTAS, a quick method for hyperspectral vision transformer architecture search. |
|
Fangqin Zhou, Mert Kilickaya, Joaquin Vanschoren BMVC 2023 arXiv / Github We propose HyLITE, a vision-transformer for Hyperspectral image classification. |
|
Mert Kilickaya, Joost van de Weijer, Yuki Asano Preprint 2023 arXiv / Slides / Github We survey semi-, few-shot, and self-supervised incremental learning. |
|
Mert Kilickaya, Joaquin Vanschoren CVPRW 2023 (Oral) arXiv / Slides We introduce VINIL, a self-supervised incremental instance learner. |
|
Mert Kilickaya, Arnold Smeulders BMVC 2021 arXiv / Slides We introduce Align-Former to detect human-object interactions from an image. |
|
Mert Kilickaya, Arnold Smeulders WACV 2021 arXiv / Slides We introduce composition-aware learning to improve visual image search. |
|
Mert Kilickaya, Aykut Erdem, Nazli Ikizler-Cinbis, Erkut Erdem EACL 2017 arXiv / Slides We propose Word-Mover Distance to evaluate image captioning. |
Patents
Visual Image Search via Conversational Interaction (Huawei)
Mert Kilickaya, Baiqiang XIA
Network for Interacted Object Localization (Qualcomm)
Mert Kilickaya, Arnold Smeulders
Subject-Object Interaction Recognition Model (Qualcomm)
Mert Kilickaya, Stratis Gavves, Arnold Smeulders
Context-driven Learning of Human-object Interactions (Qualcomm)
Mert Kilickaya, Noureldien Hussein, Stratis Gavves, Arnold Smeulders
Supervision
I am very fortunate to have crossroads with the kind souls below.
 |
Evangelos Tsimpouris (MSc, TU/e) | 2023-2024 | Learning to Transfer for Continual Learning |
 |
Fangqin Zhou (PhD, TU/e) | 2022-2024 | Locality-Aware Vision Transformers |  |
Ran Piao (MSc, TU/e) | 2022-2023 | Rapid Transformer Architecture Search without Training |  |
Tommie Kerssies (MSc, TU/e) | 2022-2023 | Test Time Adaptation |  |
Ceren Gok-Yildirim (PhD, TU/e) | 2022-2023 | Learning to Adapt for Continual Learning |  |
Kishan Parshotam (MSc, UvA) | 2020-2021 | Continual Learning of Object Instances |  |
Tarun Krishna (MSc, UvA) | 2019-2020 | Learning to rotate, scale and shift visual objects via disentanglement |
Presentations
Here are some papers from other researchers that I have enjoyed studying and presenting. Congratulations to the authors on their awesome work!
|
Source code credit to Dr. Jon Barron and ChatGPT |