Author Archives: Joost Van de Weijer - Page 2

ORGANISATION AND LOCATION: Computer Vision Center Barcelona, Spain
WEBSITE: http://www.cvc.uab.es/lamp/

DESCRIPTION OF JOB:
We are seeking a PhD to join the Learning and Machine Perception (LAMP) team in beautiful Barcelona. The position is for 4 years. LAMP is in the Computer Vision Center at the Universitat Autònoma de Barcelona and performs research on continual learning, domain adaptation, generative models, self-supervised learning, etc. The position is on an industrially sponsored project. The project is on image-to-image and image-to-video generation.

PROJECT SUPERVISOR; HOSTING GROUP
Joost van de Weijer will be the supervisor. He is the leader of the Learning and Machine Perception (LAMP) team at the CVC.

CANDIDATE ’S PROFILE
The candidate should hold a Masters degree or equivalent. The applicants are expected to be fluent in both oral and written communication in English. They should work well in a team while demonstrating initiative and independence. Prior knowledge of deep learning (Tensor Flow, Pytorch) is required.

FUNDING CONDITIONS
Living allowance of 19k€/year (gross salary).

CONTACT AND CONTACT EMAIL:
Interested applicants should email their CV (preferably with contact information of 2 references) and transcript of university course grades to Dr. Joost van de Weijer (joost@cvc.uab.es). Also, for any other inquiries please contact Joost van de Weijer.

DATES:
The position will be open until filled. The first evaluation of candidates will be July 31th. Positions should start in the new academic year (Sept, Oct) 2022.

THE COMPUTER VISION CENTER
The selected candidate will work in the Computer Vision Centre (CVC), Barcelona, a research institute comprising more than 100 researchers and support staff, dedicated to computer vision research and knowledge transfer. With a strong international projection and links to the industry, the Computer Vision Centre offers an exciting environment for scientific career development. The Computer Vision Centre has a plan for expansion of its permanent research staff base, and has received the “HR Excellence in Research” award as a provider and supporter of a stimulating and favorable working environment.

Best Paper Award CLvision 2022

Alex won the Best Paper Award at the Continual Learning Workshop at CVPR 2022 for his paper Continually Learning Self-Supervised Representations with Projected Functional Regularization. Francesco and Saurav received the runner-up award for:
Towards Exemplar-Free Continual Learning in Vision Transformers: an Account of Attention, Functional and Weight Regularization
.

Joost van de Weijer gave an invited talk at Continual Learning Workshop.

Paper at ICLR 2022

Yaxing’s paper on Distilling GANs with Style-Mixed Triplets for X2I Translation with Limited Data is accepted on ICLR 2022.

CVPR 2022

We have a total of four workshop papers at the CLVISION workshop at CVPR 2022.

We also have one additional paper at Efficient Deep Learning for Computer Vision CVPR Workshop 2022:

BMVC and WACV paper

Kai’s paper on HCV: Hierarchy-Consistency Verification for Incremental Implicitly-Refined Classification is accepted at BMVC 2021.

Also Javad’s paper Class-Balanced Active Learning for Image Classification got accepted at WACV 2022.

Paper at NeurIPS 2021

Shiqi has one paper at the NeurIPS 2021 Exploiting the Intrinsic Neighborhood Structure for Source-free Domain Adaptation.

Deep learning post-doc position

We are seeking a postdoc to join the Learning and Machine Perception (LAMP) team in beautiful Barcelona. The position is for 18 months years (could be extended by an additional year). Applications are welcome until 15th Sept. The starting date should be October/November 2021.

PROJECT SUPERVISOR & HOSTING GROUP
Joost Van de Weijer will be the supervisor. He is the leader of the Learning and Machine Perception (LAMP) team at the CVC. LAMP is in the Computer Vision Center at the Universitat Autònoma de Barcelona. The position is a sponsored industrial project with 2 postdocs and four PhD students. The subjects include lifelong learning (continual learning), generative models, reinforcement learning, and domain adaptation. For more information on the LAMP team visit:http://www.cvc.uab.es/lamp/

CANDIDATE ’S PROFILE
The candidate should possess a PhD in computer vision or machine learning, and have a strong publication record. We are looking for candidates who have publications in the top conferences CVPR, ECCV, ICCV, NIPS, ICML, or ICLR. The candidate should have a background in machine learning and deep learning. The applicants are expected to be fluent in both oral and written communication in English. We are interested in also including reinforcement learning in the project and encourage candidates with experience in this field to apply. We are looking for good team players, that demonstrate initiative and independence. The candidate is expected to supervise PhD students.

THE COMPUTER VISION CENTER
The selected candidate will work in the Computer Vision Centre (CVC), Barcelona, a research institute comprising more than 100 researchers and support staff, dedicated to artificial intelligence and computer vision research. With a strong international projection and links to the industry, the Computer Vision Centre offers an exciting environment for scientific career development. The Computer Vision Centre has a plan for expansion of its permanent research staff base, and has received the “HR Excellence in Research” award as a provider and supporter of a stimulating and favorable working environment.

RESEARCH CONTACT
If you are interested in the position, please contact Dr. Joost van de Weijer for more information and applications (jo…@cvc.uab.es)

FUNDING CONDITIONS
Living allowance of 30-40k€/year (gross salary) depending on experience

Invited Talk at CLVISION2021

Joost van de Weijer presented at the 2nd workshop on continual learning in computer vision at CVPR 2021.

See here for the video and the slides.

Code framework for Class-Incremental Learning

Check out our new framework for analysis of class-incremental learning (FACIL), which contains implementations of fourteen class-incremental algorithms and several baselines. It allows you to reproduce our results on CIFAR 100 presented in our survey paper.

Two papers at ICCV2021

Two papers have been accepted for the main track: Yaxing’s paper on TransferI2I: Transfer Learning for Image-to-Image Translation from Small Datasets. And Shiqi’s paper on Generalized Source-free Domain Adaptation (see project page).