Robert-Jan Bruintjes

PhD candidate with Jan van Gemert @ Computer Vision Lab, TU Delft

I work on supervised representation learning for Computer Vision. My main research is into integrating prior knowledge into Convolutional Neural Networks to benefit data efficiency. Topics of choice include implicit neural convolutional operators, in- and equivariant representations and data-efficiency of self-attention.

Highlights

  • Currently visiting prof. Matthias Bethge at University Tübingen

  • ICLR 2022 paper: FlexConv

  • Organizer of VIPriors workshop (2020-ongoing)

Recent

Lab visit @ University Tübingen

June 2022 I will visit the lab of prof. Matthias Bethge over the summer.

MSc supervision

June 2022 I supervised Xiangxie Zhang to achieve his MSc in Computer Science.

VIPriors challenges 2021 report

January 2022 We published a report on the VIPriors 2021 challenges.

More updates

Featured Publications

Publication January 2022 ICLR 2022 poster
FlexConv: Continuous Kernel Convolutions with Differentiable Kernel Sizes

FlexConv: Continuous Kernel Convolutions with Differentiable Kernel Sizes

We provide a high bandwidth, alias-free convolutional kernel parameterization with learnable kernel size and constant parameter cost.
ArXiv Code Poster Slides
Attila Lengyel, Robert-Jan Bruintjes, Marcos Baptista Rios, Osman Semih Kayhan, Davide Zambrano, Nergis Tomen, Jan van Gemert
Publication January 2022 ArXiv
VIPriors 2: Visual Inductive Priors for Data-Efficient Deep Learning Challenges

VIPriors 2: Visual Inductive Priors for Data-Efficient Deep Learning Challenges

We present the second edition of “VIPriors: Visual Inductive Priors for Data-Efficient Deep Learning” challenges. We offer four data-impaired challenges to encourage data efficient solutions.
Website ArXiv Code

Publications

VIPriors 2: Visual Inductive Priors for Data-Efficient Deep Learning Challenges
ArXiv Attila Lengyel, Robert-Jan Bruintjes, Marcos Baptista Rios, Osman Semih Kayhan, Davide Zambrano, Nergis Tomen, Jan van Gemert
Website ArXiv Code
FlexConv: Continuous Kernel Convolutions with Differentiable Kernel Sizes
ICLR 2022 poster David W. Romero*, Robert-Jan Bruintjes*, Jakub M. Tomczak, Erik J. Bekkers, Mark Hoogendoorn, Jan C. van Gemert
ArXiv Code Poster Slides
Domain Adaptation for Rare Classes Augmented with Synthetic Samples
ArXiv Tuhin Das, Robert-Jan Bruintjes, Attila Lengyel, Jan van Gemert, Sara Beery
ArXiv
VIPriors 1: Visual Inductive Priors for Data-Efficient Deep Learning Challenges
ArXiv Robert-Jan Bruintjes, Attila Lengyel, Marcos Baptista Rios, Osman Semih Kayhan, Jan van Gemert
Website ArXiv Code
Probabilistic multileave for online retrieval evaluation
SIGIR Anne Schuth, Robert-Jan Bruintjes, Fritjof Buüttner, Joost van Doorn, Carla Groenland, Harrie Oosterhuis, Cong-Nguyen Tran, Bas Veeling, Jos van der Velde, Roger Wechsler, David Woudenberg, Maarten de Rijke
PDF DOI

Talks and posts

On Object Detection Metrics

Read this post on Medium.
Post Sep 10, 2019 1 min read

Face Analysis Through Deep Learning

Presented as R&D Lead for Sightcorp
Talk May 8, 2019 4:00 PM
Video

Contact

I am always willing to talk about collaboration or supervision. Please find my contact info at the top of the page.

Office

TU Delft, building 28, room 5.W.600
Van Mourik Broekmanweg 6
2628 XE Delft
The Netherlands