no code implementations • 8 Oct 2021 • Dmitrii Marin, Jen-Hao Rick Chang, Anurag Ranjan, Anish Prabhu, Mohammad Rastegari, Oncel Tuzel
Token Pooling is a simple and effective operator that can benefit many architectures.
1 code implementation • ICCV 2021 • Dmitrii Marin, Yuri Boykov
Acquisition of training data for the standard semantic segmentation is expensive if requiring that each pixel is labeled.
no code implementations • CVPR 2021 • Zhongwen Zhang, Dmitrii Marin, Maria Drangova, Yuri Boykov
We are interested in unsupervised reconstruction of complex near-capillary vasculature with thousands of bifurcations where supervision and learning are infeasible.
1 code implementation • ICCV 2019 • Dmitrii Marin, Zijian He, Peter Vajda, Priyam Chatterjee, Sam Tsai, Fei Yang, Yuri Boykov
Many automated processes such as auto-piloting rely on a good semantic segmentation as a critical component.
no code implementations • CVPR 2019 • Zhongwen Zhang, Egor Chesakov, Dmitrii Marin, Yuri Boykov
We propose a new geometric regularization principle for reconstructing vector fields based on prior knowledge about their divergence.
1 code implementation • CVPR 2019 • Dmitrii Marin, Meng Tang, Ismail Ben Ayed, Yuri Boykov
Both loss functions and architectures are often explicitly tuned to be amenable to this basic local optimization.
no code implementations • 16 May 2017 • Dmitrii Marin, Meng Tang, Ismail Ben Ayed, Yuri Boykov
We call it Breiman's bias due to its similarity to the histogram mode isolation previously discovered by Breiman in decision tree learning with Gini impurity.
no code implementations • ICCV 2015 • Meng Tang, Ismail Ben Ayed, Dmitrii Marin, Yuri Boykov
Our bound formulation for kernel K-means allows to combine general pair-wise feature clustering methods with image grid regularization using graph cuts, similarly to standard color model fitting techniques for segmentation.
no code implementations • 24 Jun 2015 • Meng Tang, Dmitrii Marin, Ismail Ben Ayed, Yuri Boykov
We propose a new segmentation model combining common regularization energies, e. g. Markov Random Field (MRF) potentials, and standard pairwise clustering criteria like Normalized Cut (NC), average association (AA), etc.
no code implementations • ICCV 2015 • Dmitrii Marin, Yuri Boykov, Yuchen Zhong
Many applications in vision require estimation of thin structures such as boundary edges, surfaces, roads, blood vessels, neurons, etc.