Dr. Thomas Mensink
Research Scientist @ Google Research Amsterdam
Guest Researcher @ CV-Group, University of Amsterdam

Email: lastname -at- google.com
PublicationsCVGoogle ScholarArXiVGithubTwitterLinkedIn


  • ECCV 2022: Outstanding Reviewer recognition! I’m recognised as one of the outstanding reviewers for the ECCV 2022 conference.
  • ECCV 2022 two papers accepted! Both The Missing Link: Finding label relations across datasets (arxiv) and How stable are transferability metrics? (arxiv) have been accepted as posters to ECCV 2022. With Andrea, Michal, Jasper and Vitto!
  • Preprint. The Missing Link: Finding label relations across datasets (arxiv), with Jasper & Vitto. Abstract: Computer Vision is driven by the many datasets which are available. However, each dataset has different set of class labels, visual definition of classes, images following a specific distribution, annotation protocols, etc. In this paper we want to understand how the instances of a certain class in a dataset relate to the instances of another class in another dataset. Are they in an identity, parent/child, overlap relation? Or is there no link between them at all? We conclude that label relations cannot be established by looking at the names of classes alone, as they depend strongly on how each of the datasets was constructed.
  • Preprint. How stable are transferability metrics? (arxiv) , with Andrea, Michal, Jasper & Vitto. Abstract: Transferability metrics aim to provide heuristics for selecting the most suitable source model to transfer to a given target dataset, without fine-tuning them all. Existing works, however, rely on custom experimental setups which differ across papers. In this paper we conduct a large-scale study by systematically constructing a broad range of 715k experimental setup variations. We discover that even small variations to an experimental setup lead to different conclusions about the superiority of a transferability metric over another
  • CVPR 2022 two papers accepted on transferability for semantic segmentation and for classification: Transferability Metrics for Selecting Source Model Ensembles (arxiv, Oral) & Transferability Estimation using Bhattacharyya Class Separability (arxiv). Congrats Michal & Andrea!
  • Preprints. Two pre-prints available on transferability for semantic segmentation and for classification. See publications.
  • Accepted paper. TPAMI 2021, Factors of Influence for Transfer Learning across Diverse Appearance Domains and Task Types, with Jasper, Alina, Michael, and Vitto!
  • Accepted paper. CVIU 2021, Automatic Generation of Dense Non-rigid Optical Flow. Congrats An!
  • Accepted paper. ICML 2021, Neural Feature Matching in Implicit 3D Representations, with Yunlu, Basura, Hakan, and Stratis.
  • Accepted paper. ICLR 2021, Calibration of Neural Networks using Splines, with Kartik, Amir, Ajanthan, Cristian and Richard.
  • Accepted paper. WACV 2021, Multi-Loss Weighting with Coefficient of Variations, with Rick, Sezer and Theo.
  • Accepted paper. WACV 2021, EDEN: Synthetic Dataset of Enclosed Garden Scenes, with Hoang-An, Partha, Sezer and Theo.
  • Accepted paper. CoRL 2020, Range Conditioned Dilated Convolutions with Alex, Pei, Drago and Cristian. My first full Google paper.
  • Award. With Florent and Jorge, we received the Koenderink Award 2020 for fundamental contributions in computer vision that have withstood the test of time for our paper: Improving the Fisher Kernel for Large-Scale Image Classification, from ECCV 2010.