Maxim Berman

Computer Science · Physical Sciences

9h-index1.5kcitations27works0.02yr avg
OpenAlex↗ORCID↗Google Scholar↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Advanced Neural Network Applications(14), Domain Adaptation and Few-Shot Learning(8), Adversarial Robustness in Machine Learning(4), Advanced Image and Video Retrieval Techniques(3), Stochastic Gradient Optimization Techniques(3)

Publications27 total

YFCC100M dataset
TIB Data Manager·2024Open Access
Holidays dataset
TIB Data Manager·2024Open Access
Revisiting Evaluation Metrics for Semantic Segmentation: Optimization and Evaluation of Fine-grained Intersection over Union
arXiv (Cornell University)·2023· 9 citedOpen Access
Spatial Consistency Loss for Training Multi-Label Classifiers from Single-Label Annotations
2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)·2023Open Access
Spatial Consistency Loss for Training Multi-Label Classifiers from Single-Label Annotations
arXiv (Cornell University)·2022Open Access
Optimization for Medical Image Segmentation: Theory and Practice When Evaluating With Dice Score or Jaccard Index
IEEE Transactions on Medical Imaging·2020· 386 citedOpen Access
AOWS: Adaptive and Optimal Network Width Search With Latency Constraints
2020· 3 citedOpen Access
Discriminative Training of Conditional Random Fields with Probably Submodular Constraints
International Journal of Computer Vision·2020Open Access
Discriminative training of conditional random fields with probably\n submodular constraints
arXiv (Cornell University)·2019Open Access
A Bayesian Optimization Framework for Neural Network Compression
2019· 25 citedOpen Access
Function Norms for Neural Networks
2019· 2 citedOpen Access
Adaptive Compression-based Lifelong Learning
Socio-Environmental Systems Modeling·2019· 2 citedOpen Access
Generating superpixels using deep image representations
arXiv (Cornell University)·2019· 2 citedOpen Access
MultiGrain: a unified image embedding for classes and instances
arXiv (Cornell University)·2019· 33 citedOpen Access
Yes, IoU loss is submodular - as a function of the mispredictions
arXiv (Cornell University)·2018· 2 citedOpen Access
Supermodular Locality Sensitive Hashes
arXiv (Cornell University)·2018· 1 citedOpen Access
Efficient semantic image segmentation with superpixel pooling
arXiv (Cornell University)·2018· 18 citedOpen Access
The Lovasz-Softmax Loss: A Tractable Surrogate for the Optimization of the Intersection-Over-Union Measure in Neural Networks
2018· 937 citedOpen Access
Stochastic Weighted Function Norm Regularization.
arXiv (Cornell University)·2017· 1 citedOpen Access
Function Norms and Regularization in Deep Networks
arXiv (Cornell University)·2017· 5 citedOpen Access
page 1 of 2Next →

Frequent Co-authors

Matthew B. Blaschko(19), Amal Rannen Triki(7), Tinne Tuytelaars(3), Thomas Verelst(3), Iasonas Kokkinos(2), Amal Rannen-Triki(2), Devis Tuia(2), Jiaqian Yu(2), Tim M. Curtis(2), F. DeCampo(2), Archie C. Chapman(2), C. R. Jones(2), Paul K. Rubenstein(2), Marcin Eichner(2), Tom Eelbode(1), Jeroen Bertels(1), Dirk Vandermeulen(1), Frederik Maes(1), Raf Bisschops(1), Hervé Jeǵou(1)