I am a machine learning researcher focused on advancing deep learning, with a particular interest in multimodal intelligence. Currently, I am working as a member of technical staff at OpenAI, where I contribute to multimodal AI research.

Throughout my career, I've had the opportunity to work on various aspects of computer vision and machine learning. This includes contributing to vision model development (ImageNet state-of-the-art results in 2019, 2020, and 2021) and developing open models like SigLIP and PaliGemma. I've also worked on neural architectures including BiT, ViT, MLP-Mixer, and FlexiViT. My recent work has focused on making multimodal deep learning more accessible and scalable through projects like UViM, Vision with Rewards, and JetFormer.

I enjoy developing efficient research infrastructure, particularly using Jax. Some of this work is available in the open-source big_vision repository.

Before joining OpenAI, I was at Google Brain (now Google DeepMind). I completed my PhD at ISTA under Christoph Lampert's supervision, where I studied weakly-supervised learning and generative image models.

You can reach me at a@kolesnikov.ch.

Selected Publications

Jet: A Modern Transformer-Based Normalizing Flow

JetFormer: An Autoregressive Generative Model of Raw Images and Text

Paligemma: A versatile 3b vlm for transfer

Tuning computer vision models with task rewards

PaLI: A Jointly-Scaled Multilingual Language-Image Model

UViM: A unified modeling approach for vision with learned guiding codes

Scaling vision transformers

MLP-Mixer: An all-mlp architecture for vision

An image is worth 16x16 words: Transformers for image recognition at scale

Big transfer (BiT): General visual representation learning

iCaRL: Incremental Classifier and Representation Learning

Seed, expand and constrain: Three principles for weakly-supervised image segmentation

Publications

Jet: A Modern Transformer-Based Normalizing Flow

Authors: Alexander Kolesnikov, Andre Susano Pinto, Michael Tschannen

Year: 2024

Journal: arXiv preprint arXiv:2412.15129

arXiv PDF Code

@article{kolesnikov2024jet,
title = {Jet: A Modern Transformer-Based Normalizing Flow},
author = {Kolesnikov, Alexander and Pinto, Andre Susano and Tschannen, Michael},
journal = {arXiv preprint arXiv:2412.15129},
year = {2024}
}

JetFormer: An Autoregressive Generative Model of Raw Images and Text

Authors: Michael Tschannen, Andre Susano Pinto, Alexander Kolesnikov

Year: 2024

Journal: arXiv preprint arXiv:2411.19722

arXiv PDF

@article{tschannen2024jetformer,
title = {JetFormer: An Autoregressive Generative Model of Raw Images and Text},
author = {Tschannen, Michael and Pinto, Andre Susano and Kolesnikov, Alexander},
journal = {arXiv preprint arXiv:2411.19722},
year = {2024}
}

Paligemma: A versatile 3b vlm for transfer

Authors: Lucas Beyer, Andreas Steiner, Andre Susano Pinto, Alexander Kolesnikov, Xiao Wang, Daniel Salz, Maxim Neumann, Ibrahim Alabdulmohsin, Michael Tschannen, Emanuele Bugliarello, others

Year: 2024

Journal: arXiv preprint arXiv:2407.07726

arXiv PDF

@article{beyer2024paligemma,
title = {Paligemma: A versatile 3b vlm for transfer},
author = {Beyer, Lucas and Steiner, Andreas and Pinto, Andre Susano and Kolesnikov, Alexander and Wang, Xiao and Salz, Daniel and Neumann, Maxim and Alabdulmohsin, Ibrahim and Tschannen, Michael and Bugliarello, Emanuele and others},
journal = {arXiv preprint arXiv:2407.07726},
year = {2024}
}

A Study of Autoregressive Decoders for Multi-Tasking in Computer Vision

Authors: Lucas Beyer, Bo Wan, Gagan Madan, Filip Pavetic, Andreas Steiner, Alexander Kolesnikov, Andre Susano Pinto, Emanuele Bugliarello, Xiao Wang, Qihang Yu, Liang-Chieh Chen, Xiaohua Zhai

Year: 2023

Journal: arXiv preprint arXiv:2303.17376

arXiv PDF Code

@article{beyer2023study,
title = {A Study of Autoregressive Decoders for Multi-Tasking in Computer Vision},
author = {Beyer, Lucas and Wan, Bo and Madan, Gagan and Pavetic, Filip and Steiner, Andreas and Kolesnikov, Alexander and Pinto, Andre Susano and Bugliarello, Emanuele and Wang, Xiao and Yu, Qihang and Chen, Liang-Chieh and Zhai, Xiaohua},
journal = {arXiv preprint arXiv:2303.17376},
year = {2023}
}

Sigmoid Loss for Language Image Pre-Training

Authors: Xiaohua Zhai, Basil Mustafa, Alexander Kolesnikov, Lucas Beyer

Year: 2023

Journal: arXiv preprint arXiv:2303.15343

arXiv PDF Code

@article{zhai2023sigmoid,
title = {Sigmoid Loss for Language Image Pre-Training},
author = {Zhai, Xiaohua and Mustafa, Basil and Kolesnikov, Alexander and Beyer, Lucas},
journal = {arXiv preprint arXiv:2303.15343},
year = {2023}
}

Scaling vision transformers to 22 billion parameters

Authors: Mostafa Dehghani, Josip Djolonga, Basil Mustafa, Piotr Padlewski, Jonathan Heek, Justin Gilmer, Andreas Steiner, Mathilde Caron, Robert Geirhos, Ibrahim Alabdulmohsin, Rodolphe Jenatton, Lucas Beyer, Michael Tschannen, Anurag Arnab, Xiao Wang, Carlos Riquelme, Matthias Minderer, Joan Puigcerver, Utku Evci, Manoj Kumar, Sjoerd van Steenkiste, Gamaleldin F. Elsayed, Aravindh Mahendran, Fisher Yu, Avital Oliver, Fantine Huot, Jasmijn Bastings, Mark Patrick Collier, Alexey Gritsenko, Vighnesh Birodkar, Cristina Vasconcelos, Yi Tay, Thomas Mensink, Alexander Kolesnikov, Filip Pavetić, Dustin Tran, Thomas Kipf, Mario Lučić, Xiaohua Zhai, Daniel Keysers, Jeremiah Harmsen, Neil Houlsby

Year: 2023

Journal: arXiv preprint arXiv:2302.05442

arXiv PDF

@article{dehghani2023scaling,
title = {Scaling vision transformers to 22 billion parameters},
author = {Dehghani, Mostafa and Djolonga, Josip and Mustafa, Basil and Padlewski, Piotr and Heek, Jonathan and Gilmer, Justin and Steiner, Andreas and Caron, Mathilde and Geirhos, Robert and Alabdulmohsin, Ibrahim and Jenatton, Rodolphe and Beyer, Lucas and Tschannen, Michael and Arnab, Anurag and Wang, Xiao and Riquelme, Carlos and Minderer, Matthias and Puigcerver, Joan and Evci, Utku and Kumar, Manoj and Steenkiste, Sjoerd van and Elsayed, Gamaleldin F. and Mahendran, Aravindh and Yu, Fisher and Oliver, Avital and Huot, Fantine and Bastings, Jasmijn and Collier, Mark Patrick and Gritsenko, Alexey and Birodkar, Vighnesh and Vasconcelos, Cristina and Tay, Yi and Mensink, Thomas and Kolesnikov, Alexander and Pavetić, Filip and Tran, Dustin and Kipf, Thomas and Lučić, Mario and Zhai, Xiaohua and Keysers, Daniel and Harmsen, Jeremiah and Houlsby, Neil},
journal = {arXiv preprint arXiv:2302.05442},
year = {2023}
}

Tuning computer vision models with task rewards

Authors: André Susano Pinto, Alexander Kolesnikov, Yuge Shi, Lucas Beyer, Xiaohua Zhai

Year: 2022

Journal: arXiv preprint arXiv:2302.08242

arXiv PDF Code

@article{pinto2023tuning,
title = {Tuning computer vision models with task rewards},
author = {Pinto, André Susano and Kolesnikov, Alexander and Shi, Yuge and Beyer, Lucas and Zhai, Xiaohua},
journal = {arXiv preprint arXiv:2302.08242},
year = {2022}
}

FlexiViT: One Model for All Patch Sizes

Authors: Lucas Beyer, Pavel Izmailov, Alexander Kolesnikov, Mathilde Caron, Simon Kornblith, Xiaohua Zhai, Matthias Minderer, Michael Tschannen, Ibrahim Alabdulmohsin, Filip Pavetic

Year: 2022

Journal: Conference on Computer Vision and Pattern Recognition (CVPR)

arXiv PDF Code

@article{beyer2022flexivit,
title = {FlexiViT: One Model for All Patch Sizes},
author = {Beyer, Lucas and Izmailov, Pavel and Kolesnikov, Alexander and Caron, Mathilde and Kornblith, Simon and Zhai, Xiaohua and Minderer, Matthias and Tschannen, Michael and Alabdulmohsin, Ibrahim and Pavetic, Filip},
journal = {Conference on Computer Vision and Pattern Recognition (CVPR)},
year = {2022}
}

Pali-3 vision language models: Smaller, faster, stronger

Authors: Xi Chen, Xiao Wang, Lucas Beyer, Alexander Kolesnikov, Jialin Wu, Paul Voigtlaender, Basil Mustafa, Sebastian Goodman, Ibrahim Alabdulmohsin, Piotr Padlewski, others

Year: 2023

Journal: arXiv preprint arXiv:2310.09199

arXiv PDF

@article{chen2023pali,
title = {Pali-3 vision language models: Smaller, faster, stronger},
author = {Chen, Xi and Wang, Xiao and Beyer, Lucas and Kolesnikov, Alexander and Wu, Jialin and Voigtlaender, Paul and Mustafa, Basil and Goodman, Sebastian and Alabdulmohsin, Ibrahim and Padlewski, Piotr and others},
journal = {arXiv preprint arXiv:2310.09199},
year = {2023}
}

PaLI: A Jointly-Scaled Multilingual Language-Image Model

Authors: Xi Chen, Xiao Wang, Soravit Changpinyo, AJ Piergiovanni, Piotr Padlewski, Daniel Salz, Sebastian Goodman, Adam Grycner, Basil Mustafa, Lucas Beyer, Alexander Kolesnikov, Joan Puigcerver, Nan Ding, Keran Rong, Hassan Akbari, Gaurav Mishra, Linting Xue, Ashish Thapliyal, James Bradbury, Weicheng Kuo, Mojtaba Seyedhosseini, Chao Jia, Burcu Karagol Ayan, Carlos Riquelme, Andreas Steiner, Anelia Angelova, Xiaohua Zhai, Neil Houlsby, Radu Soricut

Year: 2022

Journal: International Conference on Representation Learning (ICLR)

arXiv PDF

@article{chen2022pali,
title = {PaLI: A Jointly-Scaled Multilingual Language-Image Model},
author = {Chen, Xi and Wang, Xiao and Changpinyo, Soravit and Piergiovanni, AJ and Padlewski, Piotr and Salz, Daniel and Goodman, Sebastian and Grycner, Adam and Mustafa, Basil and Beyer, Lucas and Kolesnikov, Alexander and Puigcerver, Joan and Ding, Nan and Rong, Keran and Akbari, Hassan and Mishra, Gaurav and Xue, Linting and Thapliyal, Ashish and Bradbury, James and Kuo, Weicheng and Seyedhosseini, Mojtaba and Jia, Chao and Ayan, Burcu Karagol and Riquelme, Carlos and Steiner, Andreas and Angelova, Anelia and Zhai, Xiaohua and Houlsby, Neil and Soricut, Radu},
journal = {International Conference on Representation Learning (ICLR)},
year = {2022}
}

UViM: A unified modeling approach for vision with learned guiding codes

Authors: Alexander Kolesnikov, André Susano Pinto, Lucas Beyer, Xiaohua Zhai, Jeremiah Harmsen, Neil Houlsby

Year: 2022

Journal: Advances in neural information processing systems (NeurIPS)

arXiv PDF Code

@article{kolesnikov2022uvim,
title = {UViM: A unified modeling approach for vision with learned guiding codes},
author = {Kolesnikov, Alexander and Susano Pinto, André and Beyer, Lucas and Zhai, Xiaohua and Harmsen, Jeremiah and Houlsby, Neil},
journal = {Advances in neural information processing systems (NeurIPS)},
year = {2022}
}

Better plain ViT baselines for ImageNet-1k

Authors: Lucas Beyer, Xiaohua Zhai, Alexander Kolesnikov

Year: 2022

Journal: arXiv preprint arXiv:2205.01580

arXiv PDF Code

@article{beyer2022better,
title = {Better plain ViT baselines for ImageNet-1k},
author = {Beyer, Lucas and Zhai, Xiaohua and Kolesnikov, Alexander},
journal = {arXiv preprint arXiv:2205.01580},
year = {2022}
}

Scaling vision transformers

Authors: Xiaohua Zhai, Alexander Kolesnikov, Neil Houlsby, Lucas Beyer

Year: 2022

Journal: Conference on Computer Vision and Pattern Recognition (CVPR)

arXiv PDF Code

@article{zhai2022scaling,
title = {Scaling vision transformers},
author = {Zhai, Xiaohua and Kolesnikov, Alexander and Houlsby, Neil and Beyer, Lucas},
journal = {Conference on Computer Vision and Pattern Recognition (CVPR)},
year = {2022}
}

Knowledge distillation: A good teacher is patient and consistent

Authors: Lucas Beyer, Xiaohua Zhai, Amélie Royer, Larisa Markeeva, Rohan Anil, Alexander Kolesnikov

Year: 2022

Journal: Conference on Computer Vision and Pattern Recognition (CVPR)

arXiv PDF Code

@article{beyer2022knowledge,
title = {Knowledge distillation: A good teacher is patient and consistent},
author = {Beyer, Lucas and Zhai, Xiaohua and Royer, Amélie and Markeeva, Larisa and Anil, Rohan and Kolesnikov, Alexander},
journal = {Conference on Computer Vision and Pattern Recognition (CVPR)},
year = {2022}
}

LiT: Zero-shot transfer with locked-image text tuning

Authors: Xiaohua Zhai, Xiao Wang, Basil Mustafa, Andreas Steiner, Daniel Keysers, Alexander Kolesnikov, Lucas Beyer

Year: 2022

Journal: Conference on Computer Vision and Pattern Recognition (CVPR)

arXiv PDF Code

@article{zhai2022lit,
title = {LiT: Zero-shot transfer with locked-image text tuning},
author = {Zhai, Xiaohua and Wang, Xiao and Mustafa, Basil and Steiner, Andreas and Keysers, Daniel and Kolesnikov, Alexander and Beyer, Lucas},
journal = {Conference on Computer Vision and Pattern Recognition (CVPR)},
year = {2022}
}

How to train your ViT? data, augmentation, and regularization in vision transformers

Authors: Andreas Steiner, Alexander Kolesnikov, Xiaohua Zhai, Ross Wightman, Jakob Uszkoreit, Lucas Beyer

Year: 2021

Journal: Transactions on Machine Learning Research (TMLR)

arXiv PDF Code

@article{steiner2021how,
title = {How to train your ViT? data, augmentation, and regularization in vision transformers},
author = {Steiner, Andreas and Kolesnikov, Alexander and Zhai, Xiaohua and Wightman, Ross and Uszkoreit, Jakob and Beyer, Lucas},
journal = {Transactions on Machine Learning Research (TMLR)},
year = {2021}
}

MLP-Mixer: An all-mlp architecture for vision

Authors: Ilya O Tolstikhin, Neil Houlsby, Alexander Kolesnikov, Lucas Beyer, Xiaohua Zhai, Thomas Unterthiner, Jessica Yung, Andreas Steiner, Daniel Keysers, Jakob Uszkoreit, others

Year: 2021

Journal: Advances in neural information processing systems (NeurIPS)

arXiv PDF Code

@article{tolstikhin2021mlp,
title = {MLP-Mixer: An all-mlp architecture for vision},
author = {Tolstikhin, Ilya O and Houlsby, Neil and Kolesnikov, Alexander and Beyer, Lucas and Zhai, Xiaohua and Unterthiner, Thomas and Yung, Jessica and Steiner, Andreas and Keysers, Daniel and Uszkoreit, Jakob and others},
journal = {Advances in neural information processing systems (NeurIPS)},
year = {2021}
}

An image is worth 16x16 words: Transformers for image recognition at scale

Authors: Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, others

Year: 2020

Journal: International Conference on Representation Learning (ICLR)

arXiv PDF Code

@article{dosovitskiy2020image,
title = {An image is worth 16x16 words: Transformers for image recognition at scale},
author = {Dosovitskiy, Alexey and Beyer, Lucas and Kolesnikov, Alexander and Weissenborn, Dirk and Zhai, Xiaohua and Unterthiner, Thomas and Dehghani, Mostafa and Minderer, Matthias and Heigold, Georg and Gelly, Sylvain and others},
journal = {International Conference on Representation Learning (ICLR)},
year = {2020}
}

Big transfer (BiT): General visual representation learning

Authors: Alexander Kolesnikov, Lucas Beyer, Xiaohua Zhai, Joan Puigcerver, Jessica Yung, Sylvain Gelly, Neil Houlsby

Year: 2020

Journal: European Conference on Computer Vision (ECCV)

arXiv PDF Code

@article{kolesnikov2020big,
title = {Big transfer (BiT): General visual representation learning},
author = {Kolesnikov, Alexander and Beyer, Lucas and Zhai, Xiaohua and Puigcerver, Joan and Yung, Jessica and Gelly, Sylvain and Houlsby, Neil},
journal = {European Conference on Computer Vision (ECCV)},
year = {2020}
}

On Robustness and Transferability of Convolutional Neural Networks

Authors: Josip Djolonga, Jessica Yung, Michael Tschannen, Rob Romijnders, Lucas Beyer, Alexander Kolesnikov, Joan Puigcerver, Matthias Minderer, Alexander D'Amour, Dan Moldovan, Sylvain Gelly, Neil Houlsby, Xiaohua Zhai, Mario Lucic

Year: 2021

Journal: Conference on Computer Vision and Pattern Recognition (CVPR)

arXiv PDF

@article{djolonga2021robustness,
title = {On Robustness and Transferability of Convolutional Neural Networks},
author = {Djolonga, Josip and Yung, Jessica and Tschannen, Michael and Romijnders, Rob and Beyer, Lucas and Kolesnikov, Alexander and Puigcerver, Joan and Minderer, Matthias and D'Amour, Alexander and Moldovan, Dan and Gelly, Sylvain and Houlsby, Neil and Zhai, Xiaohua and Lucic, Mario},
journal = {Conference on Computer Vision and Pattern Recognition (CVPR)},
year = {2021}
}

Are we done with imagenet?

Authors: Lucas Beyer, Olivier J Hénaff, Alexander Kolesnikov, Xiaohua Zhai, Aäron van den Oord

Year: 2020

Journal: arXiv preprint arXiv:2006.07159

arXiv PDF Code

@article{beyer2020we,
title = {Are we done with imagenet?},
author = {Beyer, Lucas and Hénaff, Olivier J and Kolesnikov, Alexander and Zhai, Xiaohua and Oord, Aäron van den},
journal = {arXiv preprint arXiv:2006.07159},
year = {2020}
}

A Large-scale Study of Representation Learning with the Visual Task Adaptation Benchmark

Authors: Xiaohua Zhai, Joan Puigcerver, Alexander Kolesnikov, Pierre Ruyssen, Carlos Riquelme, Mario Lucic, Josip Djolonga, Andre Susano Pinto, Maxim Neumann, Alexey Dosovitskiy, Lucas Beyer, Olivier Bachem, Michael Tschannen, Marcin Michalski, Olivier Bousquet, Sylvain Gelly, Neil Houlsby

Year: 2019

Journal: arXiv preprint arXiv:1910.04867

arXiv PDF Code

@article{zhai2019visual,
title = {A Large-scale Study of Representation Learning with the Visual Task Adaptation Benchmark},
author = {Zhai, Xiaohua and Puigcerver, Joan and Kolesnikov, Alexander and Ruyssen, Pierre and Riquelme, Carlos and Lucic, Mario and Djolonga, Josip and Pinto, Andre Susano and Neumann, Maxim and Dosovitskiy, Alexey and Beyer, Lucas and Bachem, Olivier and Tschannen, Michael and Michalski, Marcin and Bousquet, Olivier and Gelly, Sylvain and Houlsby, Neil},
journal = {arXiv preprint arXiv:1910.04867},
year = {2019}
}

S4L: Self-supervised semi-supervised learning

Authors: Xiaohua Zhai, Avital Oliver, Alexander Kolesnikov, Lucas Beyer

Year: 2019

Journal: International Conference on Computer Vision (ICCV)

arXiv PDF Code

@article{zhai2019s4l,
title = {S4L: Self-supervised semi-supervised learning},
author = {Zhai, Xiaohua and Oliver, Avital and Kolesnikov, Alexander and Beyer, Lucas},
journal = {International Conference on Computer Vision (ICCV)},
year = {2019}
}

The open images dataset v4: Unified image classification, object detection, and visual relationship detection at scale

Authors: Alina Kuznetsova, Hassan Rom, Neil Alldrin, Jasper Uijlings, Ivan Krasin, Jordi Pont-Tuset, Shahab Kamali, Stefan Popov, Matteo Malloci, Alexander Kolesnikov, Tom Duerig, Vittorio Ferrari

Year: 2020

Journal: International Journal of Computer Vision (IJCV)

arXiv PDF

@article{kuznetsova2020open,
title = {The open images dataset v4: Unified image classification, object detection, and visual relationship detection at scale},
author = {Kuznetsova, Alina and Rom, Hassan and Alldrin, Neil and Uijlings, Jasper and Krasin, Ivan and Pont-Tuset, Jordi and Kamali, Shahab and Popov, Stefan and Malloci, Matteo and Kolesnikov, Alexander and Duerig, Tom and Ferrari, Vittorio},
journal = {International Journal of Computer Vision (IJCV)},
year = {2020}
}

Detecting Visual Relationships Using Box Attention

Authors: Alexander Kolesnikov, Alina Kuznetsova, Christoph Lampert, Vittorio Ferrari

Year: 2019

Journal: International Conference on Computer Vision (ICCV) Workshops

arXiv PDF

@article{detecting2019kolesnikov,
title = {Detecting Visual Relationships Using Box Attention},
author = {Kolesnikov, Alexander and Kuznetsova, Alina and Lampert, Christoph and Ferrari, Vittorio},
journal = {International Conference on Computer Vision (ICCV) Workshops},
year = {2019}
}

Revisiting self-supervised visual representation learning

Authors: Alexander Kolesnikov, Xiaohua Zhai, Lucas Beyer

Year: 2019

Journal: Conference on Computer Vision and Pattern Recognition (CVPR)

arXiv PDF Code

@article{kolesnikov2019revisiting,
title = {Revisiting self-supervised visual representation learning},
author = {Kolesnikov, Alexander and Zhai, Xiaohua and Beyer, Lucas},
journal = {Conference on Computer Vision and Pattern Recognition (CVPR)},
year = {2019}
}

Estimating barriers to gene flow from distorted isolation-by-distance patterns

Authors: Harald Ringbauer, Alexander Kolesnikov, David L Field, Nicholas H Barton

Year: 2018

Journal: Genetics

@article{ringbauer2018estimating,
title = {Estimating barriers to gene flow from distorted isolation-by-distance patterns},
author = {Ringbauer, Harald and Kolesnikov, Alexander and Field, David L and Barton, Nicholas H},
journal = {Genetics},
year = {2018}
}

Probabilistic image colorization

Authors: Amelie Royer, Alexander Kolesnikov, Christoph H Lampert

Year: 2017

Journal: British Machine Vision Conference (BMVC)

arXiv PDF

@article{royer2017probabilistic,
title = {Probabilistic image colorization},
author = {Royer, Amelie and Kolesnikov, Alexander and Lampert, Christoph H},
journal = {British Machine Vision Conference (BMVC)},
year = {2017}
}

PixelCNN models with auxiliary variables for natural image modeling

Authors: Alexander Kolesnikov, Christoph H Lampert

Year: 2017

Journal: International Conference on Machine Learning (ICML)

arXiv PDF

@article{kolesnikov2017pixelcnn,
title = {PixelCNN models with auxiliary variables for natural image modeling},
author = {Kolesnikov, Alexander and Lampert, Christoph H},
journal = {International Conference on Machine Learning (ICML)},
year = {2017}
}

iCaRL: Incremental Classifier and Representation Learning

Authors: Sylvestre-Alvise Rebuffi, Alexander Kolesnikov, Georg Sperl, Christoph H. Lampert

Year: 2017

Journal: Conference on Computer Vision and Pattern Recognition (CVPR)

arXiv PDF Code

@article{rebuffi2017icarl,
title = {iCaRL: Incremental Classifier and Representation Learning},
author = {Rebuffi, Sylvestre-Alvise and Kolesnikov, Alexander and Sperl, Georg and Lampert, Christoph H.},
journal = {Conference on Computer Vision and Pattern Recognition (CVPR)},
year = {2017}
}

Improving weakly-supervised object localization by micro-annotation

Authors: Alexander Kolesnikov, Christoph H Lampert

Year: 2016

Journal: British Machine Vision Conference (BMVC)

arXiv PDF

@article{kolesnikov2016improving,
title = {Improving weakly-supervised object localization by micro-annotation},
author = {Kolesnikov, Alexander and Lampert, Christoph H},
journal = {British Machine Vision Conference (BMVC)},
year = {2016}
}

Seed, expand and constrain: Three principles for weakly-supervised image segmentation

Authors: Alexander Kolesnikov, Christoph H Lampert

Year: 2016

Journal: European Conference on Computer Vision (ECCV)

arXiv PDF Code

@article{kolesnikov2016seed,
title = {Seed, expand and constrain: Three principles for weakly-supervised image segmentation},
author = {Kolesnikov, Alexander and Lampert, Christoph H},
journal = {European Conference on Computer Vision (ECCV)},
year = {2016}
}

Identifying Reliable Annotations for Large Scale Image Segmentation

Authors: Alexander Kolesnikov, Christoph H Lampert

Year: 2015

Journal: arXiv preprint arXiv:1504.07460

arXiv PDF

@article{kolesnikov2015identifying,
title = {Identifying Reliable Annotations for Large Scale Image Segmentation},
author = {Kolesnikov, Alexander and Lampert, Christoph H},
journal = {arXiv preprint arXiv:1504.07460},
year = {2015}
}

Closed-form training of conditional random fields for large scale image segmentation

Authors: Alexander Kolesnikov, Matthieu Guillaumin, Vittorio Ferrari, Christoph H Lampert

Year: 2014

Journal: European Conference on Computer Vision (ECCV)

arXiv PDF

@article{kolesnikov2014closed,
title = {Closed-form training of conditional random fields for large scale image segmentation},
author = {Kolesnikov, Alexander and Guillaumin, Matthieu and Ferrari, Vittorio and Lampert, Christoph H},
journal = {European Conference on Computer Vision (ECCV)},
year = {2014}
}