Search Results for author: Olga Veksler

Found 18 papers, 1 papers with code

Regularized Loss for Weakly Supervised Single Class Semantic Segmentation

1 code implementation ECCV 2020 Olga Veksler

We propose a new weakly supervised method for training CNNs to segment an object of a single class of interest.

Object Segmentation +1

Test Time Adaptation With Regularized Loss for Weakly Supervised Salient Object Detection

no code implementations CVPR 2023 Olga Veksler

Regularized loss tends to have lower values for the more likely object segments, and thus it can be used to fine-tune an already trained CNN to a given test image, adapting to images unseen during training.

object-detection Object Detection +2

Sparse Non-Local CRF

no code implementations CVPR 2022 Olga Veksler, Yuri Boykov

We propose a new sparse non-local CRF: it has a sparse number of connections, but it has both local and non-local ones.

Semantic Segmentation

Simulating CRF with CNN for CNN

no code implementations6 May 2019 Lena Gorelick, Olga Veksler

After our CRF Simulator is trained, it can be directly incorporated as part of any larger CNN architecture, enabling a seamless end-to-end training.

Semantic Segmentation

Efficient Graph Cut Optimization for Full CRFs with Quantized Edges

no code implementations13 Sep 2018 Olga Veksler

Previous work develops efficient approximate optimization based on mean field inference, which is a local optimization method and can be far from the optimum.

Semantic Segmentation Superpixels

K-convexity shape priors for segmentation

no code implementations ECCV 2018 Hossam Isack, Lena Gorelick, Karin Ng, Olga Veksler, Yuri Boykov

As shown in the paper, for many forms of convexity our regularization model is significantly more descriptive for any given k. Our shape prior is useful in practice, e. g. in biomedical applications, and its optimization is robust to local minima.

Descriptive Object +1

Location Augmentation for CNN

no code implementations18 Jul 2018 Zhenyi Wang, Olga Veksler

For example, a salient object is more likely to be closer to the center of the image, the sky in the top part of an image, etc.

Scene Parsing Semantic Segmentation +1

Adaptive and Move Making Auxiliary Cuts for Binary Pairwise Energies

no code implementations CVPR 2017 Lena Gorelick, Yuri Boykov, Olga Veksler

First, unlike LSA-AUX which selects auxiliary functions based solely on the current solution, we propose to incorporate several additional criteria.

Efficient optimization for Hierarchically-structured Interacting Segments (HINTS)

no code implementations CVPR 2017 Hossam Isack, Olga Veksler, Ipek Oguz, Milan Sonka, Yuri Boykov

We propose an effective optimization algorithm for a general hierarchical segmentation model with geometric interactions between segments.

Segmentation

Hedgehog Shape Priors for Multi-Object Segmentation

no code implementations CVPR 2016 Hossam Isack, Olga Veksler, Milan Sonka, Yuri Boykov

In contrast to star-convexity, the tightness of our normal constraint can be changed giving better control over allowed shapes.

Descriptive Object +2

A-expansion for multiple "hedgehog" shapes

no code implementations2 Feb 2016 Hossam Isack, Yuri Boykov, Olga Veksler

A single click and +/-90 degrees normal orientation constraints reduce our hedgehog prior to star-convexity.

Segmentation Semantic Segmentation

Joint Optimization of Segmentation and Color Clustering

no code implementations ICCV 2015 Ekaterina Lobacheva, Olga Veksler, Yuri Boykov

We propose to make clustering an integral part of segmentation, by including a new clustering term in the energy function.

Clustering Segmentation

Efficient Parallel Optimization for Potts Energy With Hierarchical Fusion

no code implementations CVPR 2015 Olga Veksler

Although this is not as good as the factor of 2 approximation of the well known expansion algorithm, we achieve very good results in practice.

Submodularization for Binary Pairwise Energies

no code implementations CVPR 2014 Lena Gorelick, Yuri Boykov, Olga Veksler, Ismail Ben Ayed, Andrew Delong

We propose a general optimization framework based on local submodular approximations (LSA).

Efficient Squared Curvature

no code implementations CVPR 2014 Claudia Nieuwenhuis, Eno Toeppe, Lena Gorelick, Olga Veksler, Yuri Boykov

Curvature has received increasing attention as an important alternative to length based regularization in computer vision.

Submodularization for Quadratic Pseudo-Boolean Optimization

no code implementations8 Nov 2013 Lena Gorelick, Yuri Boykov, Olga Veksler, Ismail Ben Ayed, Andrew Delong

We propose a general optimization framework based on local submodular approximations (LSA).

Efficient Regularization of Squared Curvature

no code implementations7 Nov 2013 Claudia Nieuwenhuis, Eno Toeppe, Lena Gorelick, Olga Veksler, Yuri Boykov

Curvature has received increased attention as an important alternative to length based regularization in computer vision.

Cannot find the paper you are looking for? You can Submit a new open access paper.