@inproceedings{14448, abstract = {We consider the problem of solving LP relaxations of MAP-MRF inference problems, and in particular the method proposed recently in [16], [35]. As a key computational subroutine, it uses a variant of the Frank-Wolfe (FW) method to minimize a smooth convex function over a combinatorial polytope. We propose an efficient implementation of this subroutine based on in-face Frank-Wolfe directions, introduced in [4] in a different context. More generally, we define an abstract data structure for a combinatorial subproblem that enables in-face FW directions, and describe its specialization for tree-structured MAP-MRF inference subproblems. Experimental results indicate that the resulting method is the current state-of-art LP solver for some classes of problems. Our code is available at pub.ist.ac.at/~vnk/papers/IN-FACE-FW.html.}, author = {Kolmogorov, Vladimir}, booktitle = {Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition}, isbn = {9798350301298}, issn = {1063-6919}, location = {Vancouver, Canada}, pages = {11980--11989}, publisher = {IEEE}, title = {{Solving relaxations of MAP-MRF problems: Combinatorial in-face Frank-Wolfe directions}}, doi = {10.1109/CVPR52729.2023.01153}, volume = {2023}, year = {2023}, } @inproceedings{14114, abstract = {Algorithmic fairness is frequently motivated in terms of a trade-off in which overall performance is decreased so as to improve performance on disadvantaged groups where the algorithm would otherwise be less accurate. Contrary to this, we find that applying existing fairness approaches to computer vision improve fairness by degrading the performance of classifiers across all groups (with increased degradation on the best performing groups). Extending the bias-variance decomposition for classification to fairness, we theoretically explain why the majority of fairness methods designed for low capacity models should not be used in settings involving high-capacity models, a scenario common to computer vision. We corroborate this analysis with extensive experimental support that shows that many of the fairness heuristics used in computer vision also degrade performance on the most disadvantaged groups. Building on these insights, we propose an adaptive augmentation strategy that, uniquely, of all methods tested, improves performance for the disadvantaged groups.}, author = {Zietlow, Dominik and Lohaus, Michael and Balakrishnan, Guha and Kleindessner, Matthaus and Locatello, Francesco and Scholkopf, Bernhard and Russell, Chris}, booktitle = {2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition}, isbn = {9781665469470}, issn = {2575-7075}, location = {New Orleans, LA, United States}, pages = {10400--10411}, publisher = {Institute of Electrical and Electronics Engineers}, title = {{Leveling down in computer vision: Pareto inefficiencies in fair deep classifiers}}, doi = {10.1109/cvpr52688.2022.01016}, year = {2022}, } @inproceedings{9957, abstract = {The reflectance field of a face describes the reflectance properties responsible for complex lighting effects including diffuse, specular, inter-reflection and self shadowing. Most existing methods for estimating the face reflectance from a monocular image assume faces to be diffuse with very few approaches adding a specular component. This still leaves out important perceptual aspects of reflectance as higher-order global illumination effects and self-shadowing are not modeled. We present a new neural representation for face reflectance where we can estimate all components of the reflectance responsible for the final appearance from a single monocular image. Instead of modeling each component of the reflectance separately using parametric models, our neural representation allows us to generate a basis set of faces in a geometric deformation-invariant space, parameterized by the input light direction, viewpoint and face geometry. We learn to reconstruct this reflectance field of a face just from a monocular image, which can be used to render the face from any viewpoint in any light condition. Our method is trained on a light-stage training dataset, which captures 300 people illuminated with 150 light conditions from 8 viewpoints. We show that our method outperforms existing monocular reflectance reconstruction methods, in terms of photorealism due to better capturing of physical premitives, such as sub-surface scattering, specularities, self-shadows and other higher-order effects.}, author = {B R, Mallikarjun and Tewari, Ayush and Oh, Tae-Hyun and Weyrich, Tim and Bickel, Bernd and Seidel, Hans-Peter and Pfister, Hanspeter and Matusik, Wojciech and Elgharib, Mohamed and Theobalt, Christian}, booktitle = {Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition}, isbn = {978-166544509-2}, issn = {1063-6919}, location = {Nashville, TN, United States; Virtual}, pages = {4791--4800}, publisher = {IEEE}, title = {{Monocular reconstruction of neural face reflectance fields}}, doi = {10.1109/CVPR46437.2021.00476}, year = {2021}, } @inproceedings{7468, abstract = {We present a new proximal bundle method for Maximum-A-Posteriori (MAP) inference in structured energy minimization problems. The method optimizes a Lagrangean relaxation of the original energy minimization problem using a multi plane block-coordinate Frank-Wolfe method that takes advantage of the specific structure of the Lagrangean decomposition. We show empirically that our method outperforms state-of-the-art Lagrangean decomposition based algorithms on some challenging Markov Random Field, multi-label discrete tomography and graph matching problems.}, author = {Swoboda, Paul and Kolmogorov, Vladimir}, booktitle = {Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition}, isbn = {9781728132938}, issn = {1063-6919}, location = {Long Beach, CA, United States}, publisher = {IEEE}, title = {{Map inference via block-coordinate Frank-Wolfe algorithm}}, doi = {10.1109/CVPR.2019.01140}, volume = {2019-June}, year = {2019}, } @inproceedings{18287, abstract = {Many algorithms for the computation of correspondences between deformable shapes rely on some variant of nearest neighbor matching in a descriptor space. Such are, for example, various point-wise correspondence recovery algorithms used as a post-processing stage in the functional correspondence framework. Such frequently used techniques implicitly make restrictive assumptions (e.g., nearisometry) on the considered shapes and in practice suffer from lack of accuracy and result in poor surjectivity. We propose an alternative recovery technique capable of guaranteeing a bijective correspondence and producing significantly higher accuracy and smoothness. Unlike other methods our approach does not depend on the assumption that the analyzed shapes are isometric. We derive the proposed method from the statistical framework of kernel density estimation and demonstrate its performance on several challenging deformable 3D shape matching datasets.}, author = {Vestner, Matthias and Litman, Roee and Rodola, Emanuele and Bronstein, Alexander and Cremers, Daniel}, booktitle = {2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)}, isbn = {9781538604588}, issn = {1063-6919}, location = {Honolulu, HI, United States}, pages = {6681 -- 6690}, publisher = {IEEE}, title = {{Product manifold filter: Non-rigid shape correspondence via kernel density estimation in the product space}}, doi = {10.1109/cvpr.2017.707}, year = {2017}, } @inproceedings{3700, abstract = {We propose a new method to partition an unlabeled dataset, called Discriminative Context Partitioning (DCP). It is motivated by the idea of splitting the dataset based only on how well the resulting parts can be separated from a context class of disjoint data points. This is in contrast to typical clustering techniques like K-means that are based on a generative model by implicitly or explicitly searching for modes in the distribution of samples. The discriminative criterion in DCP avoids the problems that density based methods have when the a priori assumption of multimodality is violated, when the number of samples becomes small in relation to the dimensionality of the feature space, or if the cluster sizes are strongly unbalanced. We formulate DCP‘s separation property as a large-margin criterion, and show how the resulting optimization problem can be solved efficiently. Experiments on the MNIST and USPS datasets of handwritten digits and on a subset of the Caltech256 dataset show that, given a suitable context, DCP can achieve good results even in situation where density-based clustering techniques fail.}, author = {Lampert, Christoph}, booktitle = {2008 IEEE Conference on Computer Vision and Pattern Recognition}, isbn = {9781424422425}, issn = {1063-6919}, location = {Anchorage, AK, United States}, pages = {1 -- 8}, publisher = {IEEE}, title = {{Partitioning of image datasets using discriminative context information}}, doi = {10.1109/CVPR.2008.4587448}, year = {2008}, } @inproceedings{3712, abstract = {We present a new method for spectral clustering with paired data based on kernel canonical correlation analysis, called correlational spectral clustering. Paired data are common in real world data sources, such as images with text captions. Traditional spectral clustering algorithms either assume that data can be represented by a single similarity measure, or by co-occurrence matrices that are then used in biclustering. In contrast, the proposed method uses separate similarity measures for each data representation, and allows for projection of previously unseen data that are only observed in one representation (e.g. images but not text). We show that this algorithm generalizes traditional spectral clustering algorithms and show consistent empirical improvement over spectral clustering on a variety of datasets of images with associated text.}, author = {Blaschko, Matthew and Lampert, Christoph}, booktitle = {2008 IEEE Conference on Computer Vision and Pattern Recognition}, isbn = {9781424422425}, issn = {1063-6919}, location = {Anchorage, AK, United States}, pages = {1 -- 8}, publisher = {IEEE}, title = {{Correlational spectral clustering}}, doi = {10.1109/CVPR.2008.4587353}, year = {2008}, } @inproceedings{3714, abstract = {Most successful object recognition systems rely on binary classification, deciding only if an object is present or not, but not providing information on the actual object location. To perform localization, one can take a sliding window approach, but this strongly increases the computational cost, because the classifier function has to be evaluated over a large set of candidate subwindows. In this paper, we propose a simple yet powerful branchand- bound scheme that allows efficient maximization of a large class of classifier functions over all possible subimages. It converges to a globally optimal solution typically in sublinear time. We show how our method is applicable to different object detection and retrieval scenarios. The achieved speedup allows the use of classifiers for localization that formerly were considered too slow for this task, such as SVMs with a spatial pyramid kernel or nearest neighbor classifiers based on the 2-distance. We demonstrate state-of-the-art performance of the resulting systems on the UIUC Cars dataset, the PASCAL VOC 2006 dataset and in the PASCAL VOC 2007 competition.}, author = {Lampert, Christoph and Blaschko, Matthew and Hofmann, Thomas}, booktitle = {2008 IEEE Conference on Computer Vision and Pattern Recognition}, isbn = {9781424422425}, issn = {1063-6919}, location = {Anchorage, AK, United States}, pages = {1 -- 8}, publisher = {IEEE}, title = {{Beyond sliding windows: Object localization by efficient subwindow search}}, doi = {10.1109/CVPR.2008.4587586}, year = {2008}, } @inproceedings{3183, abstract = {This paper describes two algorithms capable of real-time segmentation of foreground from background layers in stereo video sequences. Automatic separation of layers from colour/contrast or from stereo alone is known to be error-prone. Here, colour, contrast and stereo matching information are fused to infer layers accurately and efficiently. The first algorithm, Layered Dynamic Programming (LDP), solves stereo in an extended 6-state space that represents both foreground/background layers and occluded regions. The stereo-match likelihood is then fused with a contrast-sensitive colour model that is learned on the fly, and stereo disparities are obtained by dynamic programming. The second algorithm, Layered Graph Cut (LGC), does not directly solve stereo. Instead the stereo match likelihood is marginalised over foreground and background hypotheses, and fused with a contrast-sensitive colour model like the one used in LDP. Segmentation is solved efficiently by ternary graph cut. Both algorithms are evaluated with respect to ground truth data and found to have similar perfomance, substantially better than stereo or colour/contrast alone. However, their characteristics with respect to computational efficiency are rather different. The algorithms are demonstrated in the application of background substitution and shown to give good quality composite video output.}, author = {Kolmogorov, Vladimir and Criminisi, Antonio and Blake, Andrew and Cross, Geoffrey and Rother, Carsten}, booktitle = {Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Volume 2 }, isbn = {0769523722}, issn = {1063-6919}, location = {San Diego, CA, United States}, pages = {407 -- 414}, publisher = {IEEE}, title = {{Bi-layer segmentation of binocular stereo video}}, doi = {10.1109/CVPR.2005.91}, volume = {2}, year = {2005}, } @inproceedings{3175, abstract = {This paper addresses the novel problem of automatically synthesizing an output image from a large collection of different input images. The synthesized image, called a digital tapestry, can be viewed as a visual summary or a virtual 'thumbnail' of all the images in the input collection. The problem of creating the tapestry is cast as a multi-class labeling problem such that each region in the tapestry is constructed from input image blocks that are salient and such that neighboring blocks satisfy spatial compatibility. This is formulated using a Markov Random Field and optimized via the graph cut based expansion move algorithm. The standard expansion move algorithm can only handle energies with metric terms, while our energy contains non-metric (soft and hard) constraints. Therefore we propose two novel contributions. First, we extend the expansion move algorithm for energy functions with non-metric hard constraints. Secondly, we modify it for functions with "almost" metric soft terms, and show that it gives good results in practice. The proposed framework was tested on several consumer photograph collections, and the results are presented.}, author = {Rother, Carsten and Kumar, Sanjiv and Kolmogorov, Vladimir and Blake, Andrew}, booktitle = {Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Volume 1}, isbn = {0769523722}, issn = {1063-6919}, location = {San Diego, CA, United States}, pages = {589 -- 596}, publisher = {IEEE}, title = {{Digital tapestry}}, doi = {10.1109/CVPR.2005.130}, volume = {1}, year = {2005}, } @inproceedings{3176, abstract = {This paper demonstrates the high quality, real-time segmentation techniques. We achieve real-time segmentation of foreground from background layers in stereo video sequences. Automatic separation of layers from colour/contrast or from stereo alone is known to be error-prone. Here, colour, contrast and stereo matching information are fused to infer layers accurately and efficiently. The first algorithm, layered dynamic programming (LDP), solves stereo in an extended 6-state space that represents both foreground/background layers and occluded regions. The stereo-match likelihood is then fused with a contrast-sensitive colour model that is learned on the fly, and stereo disparities are obtained by dynamic programming. The second algorithm, layered graph cut (LGC), does not directly solve stereo. Instead the stereo match likelihood is marginalised over foreground and background hypotheses, and fused with a contrast-sensitive colour model like the one used in LDP. Segmentation is solved efficiently by ternary graph cut. Both algorithms are evaluated with respect to ground truth data and found to have similar performance, substantially better than stereo or colour/contrast alone. However, their characteristics with respect to computational efficiency are rather different. The algorithms are demonstrated in the application of background substitution and shown to give good quality composite video output. }, author = {Kolmogorov, Vladimir and Criminisi, Antonio and Blake, Andrew and Cross, Geoffrey and Rother, Carsten}, booktitle = {Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition}, isbn = {0769523722}, issn = {1063-6919}, location = {San Diego, CA, United States}, pages = {1186 -- 1186}, publisher = {IEEE}, title = {{Bi-layer segmentation of binocular stereo video}}, doi = {10.1109/CVPR.2005.90}, year = {2005}, }