8 citations · 21 across the 7 of their papers we have counts for
8 papers · 1 filter
Occlusion-Ordered Semantic Instance Segmentation
Soroosh Baselizadeh, Cheuk-To Yu, Olga Veksler +1
Standard semantic instance segmentation provides useful, but inherently 2D information from a single image. To enable 3D analysis, one usually integrates absolute monocular depth e…
Simulating CRF with CNN for CNN
Lena Gorelick, Olga Veksler
Combining CNN with CRF for modeling dependencies between pixel labels is a popular research direction. This task is far from trivial, especially if end-to-end training is desired.…
Efficient Graph Cut Optimization for Full CRFs with Quantized Edges
Olga Veksler
Fully connected pairwise Conditional Random Fields (Full-CRF) with Gaussian edge weights can achieve superior results compared to sparsely connected CRFs. However, traditional meth…
Location Augmentation for CNN
Zhenyi Wang, Olga Veksler
CNNs have made a tremendous impact on the field of computer vision in the last several years. The main component of any CNN architecture is the convolution operation, which is tran…
Efficient optimization for Hierarchically-structured Interacting Segments (HINTS)
Hossam Isack, Olga Veksler, Ipek Oguz +2
We propose an effective optimization algorithm for a general hierarchical segmentation model with geometric interactions between segments. Any given tree can specify a partial orde…
A-expansion for multiple "hedgehog" shapes
Hossam Isack, Yuri Boykov, Olga Veksler
Overlapping colors and cluttered or weak edges are common segmentation problems requiring additional regularization. For example, star-convexity is popular for interactive single o…
Submodularization for Quadratic Pseudo-Boolean Optimization
Lena Gorelick, Yuri Boykov, Olga Veksler +2
Many computer vision problems require optimization of binary non-submodular energies. We propose a general optimization framework based on local submodular approximations (LSA). Un…
Efficient Regularization of Squared Curvature
Claudia Nieuwenhuis, Eno Toeppe, Lena Gorelick +2
Curvature has received increased attention as an important alternative to length based regularization in computer vision. In contrast to length, it preserves elongated structures a…