Maxim Berman
Maxim Berman
Verified email at - Homepage
Cited by
Cited by
The Lovász-Softmax loss: A tractable surrogate for the optimization of the intersection-over-union measure in neural networks
M Berman, A Rannen Triki, MB Blaschko
Optimizing the dice score and jaccard index for medical image segmentation: Theory and practice
J Bertels, T Eelbode, M Berman, D Vandermeulen, F Maes, R Bisschops, ...
Medical Image Computing and Computer Assisted Intervention–MICCAI 2019: 22nd …, 2019
Optimization for medical image segmentation: theory and practice when evaluating with dice score or jaccard index
T Eelbode, J Bertels, M Berman, D Vandermeulen, F Maes, R Bisschops, ...
IEEE transactions on medical imaging 39 (11), 3679-3690, 2020
Multigrain: a unified image embedding for classes and instances
M Berman, H Jégou, A Vedaldi, I Kokkinos, M Douze
arXiv preprint arXiv:1902.05509, 2019
Aows: Adaptive and optimal network width search with latency constraints
M Berman, L Pishchulin, N Xu, MB Blaschko, G Medioni
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2020
Optimization of the Jaccard index for image segmentation with the Lovász hinge.
M Berman, MB Blaschko
CoRR, 2017
A Bayesian Optimization Framework for Neural Network Compression
X Ma, A Rannen Ep Triki, M Berman, C Sagonas, J Cali, MB Blaschko
Proceedings of the IEEE International Conference on Computer Vision, 2019
Spatial consistency loss for training multi-label classifiers from single-label annotations
T Verelst, PK Rubenstein, M Eichner, T Tuytelaars, M Berman
Proceedings of the IEEE/CVF Winter Conference on Applications of Computer …, 2023
Efficient semantic image segmentation with superpixel pooling
M Schuurmans, M Berman, MB Blaschko
arXiv preprint arXiv:1806.02705, 2018
Adaptive compression-based lifelong learning
S Srivastava, M Berman, MB Blaschko, D Tuia
arXiv preprint arXiv:1907.09695, 2019
Function norms and regularization in deep networks
AR Triki, M Berman, MB Blaschko
arXiv preprint arXiv:1710.06703, 2017
Generating superpixels using deep image representations
T Verelst, M Blaschko, M Berman
arXiv preprint arXiv:1903.04586, 2019
Function norms for neural networks
A Rannen-Triki, M Berman, V Kolmogorov, MB Blaschko
Proceedings of the IEEE/CVF International Conference on Computer Vision …, 2019
Revisiting evaluation metrics for semantic segmentation: Optimization and evaluation of fine-grained intersection over union
Z Wang, M Berman, A Rannen-Triki, P Torr, D Tuia, T Tuytelaars, LV Gool, ...
Advances in Neural Information Processing Systems 36, 2024
Generating superpixels with deep representations
T Verelst, M Berman
CVPR 2018 workshop on DeepVision: Beyond supervised learning, Date: 2018/06 …, 2018
Monocular surface reconstruction using 3D deformable part models
S Kinauer, M Berman, I Kokkinos
Computer Vision–ECCV 2016 Workshops: Amsterdam, The Netherlands, October 8 …, 2016
Supermodular Locality Sensitive Hashes
M Berman, MB Blaschko
arXiv preprint arXiv:1807.06686, 2018
Stochastic weighted function norm regularization
AR Triki, M Berman, MB Blaschko
CoRR, 2017
Tractable Approximations for Achieving Higher Model Efficiency in Computer Vision
M Berman
Discriminative training of conditional random fields with probably submodular constraints
M Berman, MB Blaschko
International Journal of Computer Vision 128 (6), 1722-1735, 2020
The system can't perform the operation now. Try again later.
Articles 1–20