Search Results for author:
Found 37 papers, 5 papers with code
Collision Cross-entropy for Soft Class Labels and Deep Clustering
We propose "collision cross-entropy" as a robust alternative to Shannon's cross-entropy (CE) loss when class labels are represented by soft categorical distributions y.
Discriminative Entropy Clustering and its Relation to K-means and SVM
Maximization of mutual information between the model's input and output is formally related to "decisiveness" and "fairness" of the softmax predictions, motivating such unsupervised entropy-based losses for discriminative models.
Sparse Non-Local CRF
We propose a new sparse non-local CRF: it has a sparse number of connections, but it has both local and non-local ones.
Robust Trust Region for Weakly Supervised Segmentation
Acquisition of training data for the standard semantic segmentation is expensive if requiring that each pixel is labeled.
Confluent Vessel Trees with Accurate Bifurcations
We are interested in unsupervised reconstruction of complex near-capillary vasculature with thousands of bifurcations where supervision and learning are infeasible.
RePose: Learning Deep Kinematic Priors for Fast Human Pose Estimation
At the coarsest resolution, and in a manner similar to classical part-based approaches, we leverage the kinematic structure of the human body to propagate convolutional feature updates between the keypoints or body parts.
Image Segmentation Using Deep Learning: A Survey
Image segmentation is a key topic in image processing and computer vision with applications such as scene understanding, medical image analysis, robotic perception, video surveillance, augmented reality, and image compression, among many others.
Efficient Segmentation: Learning Downsampling Near Semantic Boundaries
Many automated processes such as auto-piloting rely on a good semantic segmentation as a critical component.
Divergence Prior and Vessel-tree Reconstruction
We propose a new geometric regularization principle for reconstructing vector fields based on prior knowledge about their divergence.
Beyond Gradient Descent for Regularized Segmentation Losses
Both loss functions and architectures are often explicitly tuned to be amenable to this basic local optimization.
K-convexity shape priors for segmentation
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.
Constrained-CNN losses for weakly supervised segmentation
To the best of our knowledge, the method of [Pathak et al., 2015] is the only prior work that addresses deep CNNs with linear constraints in weakly supervised segmentation.
Normalized Cut Loss for Weakly-supervised CNN Segmentation
Our normalized cut loss approach to segmentation brings the quality of weakly-supervised training significantly closer to fully supervised methods.
On Regularized Losses for Weakly-supervised CNN Segmentation
This approach simplifies weakly-supervised training by avoiding extra MRF/CRF inference steps or layers explicitly generating full masks, while improving both the quality and efficiency of training.
Adaptive and Move Making Auxiliary Cuts for Binary Pairwise Energies
First, unlike LSA-AUX which selects auxiliary functions based solely on the current solution, we propose to incorporate several additional criteria.
Kernel clustering: density biases and solutions
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.
Efficient optimization for Hierarchically-structured Interacting Segments (HINTS)
We propose an effective optimization algorithm for a general hierarchical segmentation model with geometric interactions between segments.
Hedgehog Shape Priors for Multi-Object Segmentation
In contrast to star-convexity, the tightness of our normal constraint can be changed giving better control over allowed shapes.
A-expansion for multiple "hedgehog" shapes
A single click and +/-90 degrees normal orientation constraints reduce our hedgehog prior to star-convexity.
Joint Optimization of Segmentation and Color Clustering
We propose to make clustering an integral part of segmentation, by including a new clustering term in the energy function.
Secrets of GrabCut and Kernel K-Means
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.
Kernel Cuts: MRF meets Kernel & Spectral Clustering
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.
Thin Structure Estimation with Curvature Regularization
Many applications in vision require estimation of thin structures such as boundary edges, surfaces, roads, blood vessels, neurons, etc.
Volumetric Bias in Segmentation and Reconstruction: Secrets and Solutions
Many standard optimization methods for segmentation and reconstruction compute ML model estimates for appearance or geometry of segments, e. g. Zhu-Yuille 1996, Torr 1998, Chan-Vese 2001, GrabCut 2004, Delong et al. 2012.
Joint Energy-based Detection and Classificationon of Multilingual Text Lines
This paper proposes a new hierarchical MDL-based model for a joint detection and classification of multilingual text lines in im- ages taken by hand-held cameras.
Energy Based Multi-model Fitting & Matching for 3D Reconstruction
Standard geometric model fitting methods take as an input a fixed set of feature pairs greedily matched based only on their appearances.
Efficient Squared Curvature
Curvature has received increasing attention as an important alternative to length based regularization in computer vision.
Submodularization for Binary Pairwise Energies
We propose a general optimization framework based on local submodular approximations (LSA).
An Experimental Comparison of Trust Region and Level Sets
High-order (non-linear) functionals have become very popular in segmentation, stereo and other computer vision problems.
Submodularization for Quadratic Pseudo-Boolean Optimization
We propose a general optimization framework based on local submodular approximations (LSA).
Efficient Regularization of Squared Curvature
Curvature has received increased attention as an important alternative to length based regularization in computer vision.
In Defense of 3D-Label Stereo
Our theoretical and experimental results demonstrate advantages over state-of-the-art methods for 2nd order smoothness stereo.
Auxiliary Cuts for General Classes of Higher Order Functionals
From these general-form bounds, we state various non-linear problems as the optimization of auxiliary functionals by graph cuts.
Fast Trust Region for Segmentation
In this paper we propose a Fast Trust Region (FTR) approach for optimization of segmentation energies with nonlinear regional terms, which are known to be challenging for existing algorithms.
Joint optimization of fitting & matching in multi-view reconstruction
In contrast, we solve feature matching and multi-model fitting problems in a joint optimization framework.
Simplifying Energy Optimization using Partial Enumeration
Energies with high-order non-submodular interactions have been shown to be very useful in vision due to their high modeling power.
Minimizing Sparse High-Order Energies by Submodular Vertex-Cover
Inference on high-order graphical models has become increasingly important in recent years.
