Fredrik Löfman

Joined

May 2022

Names

Fredrik Löfman (Preferred)

Fredrik Carlsson

Emails

****@raysearchlabs.com (Confirmed)

Personal Links

DBLP

Career & Education History

PhD student

KTH Royal Institute of Technology (kth.se)

2003 – 2008

MS student

Imperial College London, Imperial College London (imperial.ac.uk)

2002 – 2003

MS student

Chalmers University of Technology (chalmers.se)

1998 – 2002

Advisors, Relations & Conflicts

PhD Advisee

Marcus Nordström

2017 – Present

PhD Advisor

Anders Forsgren

2003 – 2008

Expertise

medical image segmentation

2017 – Present

deep learning

CNNs

U-Net

2017 – Present

nonlinear optimization

2003 – Present

Publications

On Image Segmentation With Noisy Labels: Characterization and Volume Properties of the Optimal Solutions to Accuracy and Dice
Marcus Nordstrom, Henrik Hult, Fredrik Löfman, Jonas Söderberg
- Published: 31 Oct 2022, Last Modified: 14 Jan 2023
- NeurIPS 2022 Accept
- Readers: Everyone
On Image Segmentation With Noisy Labels: Characterization and Volume Properties of the Optimal Solutions to Accuracy and Dice
Marcus Nordström, Henrik Hult, Jonas Söderberg, Fredrik Löfman
- 2022 (modified: 12 Nov 2022)
- CoRR 2022
- Readers: Everyone
Calibrated Surrogate Maximization of Dice
Marcus Nordström, Han Bao, Fredrik Löfman, Henrik Hult, Atsuto Maki, Masashi Sugiyama
- 2020 (modified: 12 Nov 2022)
- MICCAI (4) 2020
- Readers: Everyone
On column generation approaches for approximate solutions of quadratic programs in intensity-modulated radiation therapy
Fredrik Carlsson, Anders Forsgren
- 2014 (modified: 12 Nov 2022)
- Ann. Oper. Res. 2014
- Readers: Everyone
Using eigenstructure of the Hessian to reduce the dimension of the intensity modulated radiation therapy optimization problem
Fredrik Carlsson, Anders Forsgren, Henrik Rehbinder, Kjell Eriksson
- 2006 (modified: 12 Nov 2022)
- Ann. Oper. Res. 2006
- Readers: Everyone

Fredrik Löfman

Names

Emails

Personal Links

Career & Education History

Advisors, Relations & Conflicts

Expertise

Publications

On Image Segmentation With Noisy Labels: Characterization and Volume Properties of the Optimal Solutions to Accuracy and Dice

On Image Segmentation With Noisy Labels: Characterization and Volume Properties of the Optimal Solutions to Accuracy and Dice

Calibrated Surrogate Maximization of Dice

On column generation approaches for approximate solutions of quadratic programs in intensity-modulated radiation therapy

Using eigenstructure of the Hessian to reduce the dimension of the intensity modulated radiation therapy optimization problem

Co-Authors