@conference {Adler2019, title = {Out of Distribution Detection for Intra-operative Functional Imaging}, booktitle = {MICCAI UNSURE Workshop 2019}, volume = {11840 LNCS}, year = {2019}, pages = {75{\textendash}82}, abstract = {Multispectral optical imaging is becoming a key tool in the operating room. Recent research has shown that machine learning algorithms can be used to convert pixel-wise reflectance measurements to tissue parameters, such as oxygenation. However, the accuracy of these algorithms can only be guaranteed if the spectra acquired during surgery match the ones seen during training. It is therefore of great interest to detect so-called out of distribution (OoD) spectra to prevent the algorithm from presenting spurious results. In this paper we present an information theory based approach to OoD detection based on the widely applicable information criterion (WAIC). Our work builds upon recent methodology related to invertible neural networks (INN). Specifically, we make use of an ensemble of INNs as we need their tractable Jacobians in order to compute the WAIC. Comprehensive experiments with in silico, and in vivo multispectral imaging data indicate that our approach is well-suited for OoD detection. Our method could thus be an important step towards reliable functional imaging in the operating room.}, issn = {16113349}, doi = {10.1007/978-3-030-32689-0_8}, author = {Adler, Tim J and Ayala, Leonardo and Lynton Ardizzone and Kenngott, Hannes G and Vemuri, Anant and M{\"u}ller-Stich, Beat P and Carsten Rother and Ullrich K{\"o}the and Maier-Hein, Lena} } @conference {Zheng2015, title = {Object proposals estimation in depth image using compact 3D shape manifolds}, booktitle = {Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics)}, volume = {9358}, year = {2015}, pages = {196{\textendash}208}, abstract = {Man-made objects, such as chairs, often have very large shape variations, making it challenging to detect them. In this work we investigate the task of finding particular object shapes from a single depth image. We tackle this task by exploiting the inherently low dimensionality in the object shape variations, which we discover and encode as a compact shape space. Starting from any collection of 3D models, we first train a low dimensional Gaussian Process Latent Variable Shape Space. We then sample this space, effectively producing infinite amounts of shape variations, which are used for training. Additionally, to support fast and accurate inference, we improve the standard 3D object category proposal generation pipeline by applying a shallow convolutional neural network-based filtering stage. This combination leads to considerable improvements for proposal generation, in both speed and accuracy. We compare our full system to previous state-of-the-art approaches, on four different shape classes, and show a clear improvement.}, isbn = {9783319249469}, issn = {16113349}, doi = {10.1007/978-3-319-24947-6_16}, author = {Zheng, Shuai and Prisacariu, Victor Adrian and Averkiou, Melinos and Cheng, Ming Ming and Mitra, Niloy J and Shotton, Jamie and Torr, Philip H.S. and Carsten Rother} } @article {Jug2014, title = {Optimal joint segmentation and tracking of escherichia coli in the mother machine}, journal = {Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics)}, volume = {8677}, year = {2014}, pages = {25{\textendash}36}, abstract = {We introduce a graphical model for the joint segmentation and tracking of E. coli cells from time lapse videos. In our setup cells are grown in narrow columns (growth channels) in a so-called {\textquotedblleft}Mother Machine{\textquotedblright} [1]. In these growth channels, cells are vertically aligned, grow and divide over time, and eventually leave the channel at the top. The model is built on a large set of cell segmentation hypotheses for each video frame that we extract from data using a novel parametric max-flow variation. Possible tracking assignments between segments across time, including cell identity mapping, cell division, and cell exit events are enumerated. Each such assignment is represented as a binary decision variable with unary costs based on image and object features of the involved segments. We find a cost-minimal and consistent solution by solving an integer linear program. We introduce a new and important type of constraint that ensures that cells exit the Mother Machine in the correct order. Our method finds a globally optimal tracking solution with an accuracy of > 95\% (1.22 times the inter-observer error) and is on average 2 - 11 times faster than the microscope produces the raw data.}, issn = {16113349}, doi = {10.1007/978-3-319-12289-2_3}, author = {Jug, Florian and Pietzsch, Tobias and Kainm{\"u}ller, Dagmar and Funke, Jan and Kaiser, Matthias and van Nimwegen, Erik and Carsten Rother and Myers, Gene} } @conference {Vicente2011, title = {Object cosegmentation}, booktitle = {Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition}, year = {2011}, pages = {2217{\textendash}2224}, abstract = {Cosegmentation is typically defined as the task of jointly segmenting something similar in a given set of images. Existing methods are too generic and so far have not demonstrated competitive results for any specific task. In this paper we overcome this limitation by adding two new aspects to cosegmentation: (1) the "something" has to be an object, and (2) the "similarity" measure is learned. In this way, we are able to achieve excellent results on the recently introduced iCoseg dataset, which contains small sets of images of either the same object instance or similar objects of the same class. The challenge of this dataset lies in the extreme changes in viewpoint, lighting, and object deformations within each set. We are able to considerably outperform several competitors. To achieve this performance, we borrow recent ideas from object recognition: the use of powerful features extracted from a pool of candidate object-like segmentations. We believe that our work will be beneficial to several application areas, such as image retrieval. {\textcopyright} 2011 IEEE.}, isbn = {9781457703942}, issn = {10636919}, doi = {10.1109/CVPR.2011.5995530}, author = {Vicente, Sara and Carsten Rother and Kolmogorov, Vladimir} } @conference {Bleyer2011, title = {Object stereo Joint stereo matching and object segmentation}, booktitle = {Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition}, year = {2011}, pages = {3081{\textendash}3088}, abstract = {This paper presents a method for joint stereo matching and object segmentation. In our approach a 3D scene is represented as a collection of visually distinct and spatially coherent objects. Each object is characterized by three different aspects: a color model, a 3D plane that approximates the object{\textquoteright}s disparity distribution, and a novel 3D connectivity property. Inspired by Markov Random Field models of image segmentation, we employ object-level color models as a soft constraint, which can aid depth estimation in powerful ways. In particular, our method is able to recover the depth of regions that are fully occluded in one input view, which to our knowledge is new for stereo matching. Our model is formulated as an energy function that is optimized via fusion moves. We show high-quality disparity and object segmentation results on challenging image pairs as well as standard benchmarks. We believe our work not only demonstrates a novel synergy between the areas of image segmentation and stereo matching, but may also inspire new work in the domain of automatic and interactive object-level scene manipulation. {\textcopyright} 2011 IEEE.}, isbn = {9781457703942}, issn = {10636919}, doi = {10.1109/CVPR.2011.5995581}, author = {Bleyer, Michael and Carsten Rother and Kohli, Pushmeet and Scharstein, Daniel and Sinha, Sudipta} } @conference {Rother2007a, title = {Optimizing binary MRFs via extended roof duality}, booktitle = {Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition}, year = {2007}, abstract = {Many computer vision applications rely on the efficient optimization of challenging, so-called non-submodular, binary pairwise MRFs. A promising graph cut based approach for optimizing such MRFs known as "roof duality" was recently introduced into computer vision. We study two methods which extend this approach. First, we discuss an efficient implementation of the "probing" technique introduced recently by Boros et al. [5]. It simplifies the MRF while preserving the global optimum. Our code is 400-700 faster on some graphs than the implementation of [5]. Second, we present a new technique which takes an arbitrary input labeling and tries to improve its energy. We give theoretical characterizations of local minima of this procedure. We applied both techniques to many applications, including image segmentation, new view synthesis, superresolution, diagram recognition, parameter learning, texture restoration, and image deconvolution. For several applications we see that we are able to find the global minimum very efficiently, and considerably outperform the original roof duality approach. In comparison to existing techniques, such as graph cut, TRW, BP, ICM, and simulated annealing, we nearly always find a lower energy. {\textcopyright} 2007 IEEE.}, isbn = {1424411807}, issn = {10636919}, doi = {10.1109/CVPR.2007.383203}, author = {Carsten Rother and Kolmogorov, Vladimir and Lempitsky, Victor and Szummer, Martin} } @article {Rother2007, title = {Optimizing Binary MRFs via Extended Roof Duality Technical Report MSR-TR-2007-46}, journal = {Computing}, year = {2007}, abstract = {Many computer vision applications rely on the efficient optimization of challenging, so-called non-submodular, binary pairwise MRFs. A promising graph cut based approach for optimizing such MRFs known as "roof duality" was recently introduced into computer vision. We study two methods which extend this approach. First, we discuss an efficient implementation of the "probing" technique introduced recently by Boros et al. [8]. It simplifies the MRF while preserving the global optimum. Our code is 400-700 faster on some graphs than the implementation of [8]. Second , we present a new technique which takes an arbitrary input labeling and tries to improve its energy. We give theoretical characterizations of local minima of this procedure. We applied both techniques to many applications, including image segmentation, new view synthesis, super-resolution, diagram recognition, parameter learning, texture restoration, and image deconvolution. For several applications we see that we are able to find the global minimum very efficiently, and considerably outperform the original roof duality approach. In comparison to existing techniques , such as graph cut, TRW, BP, ICM, and simulated annealing, we nearly always find a lower energy.}, url = {http://research.microsoft.com/vision/cambridge/}, author = {Carsten Rother and Kolmogorov, Vladimir and Lempitsky, Victor and Szummer, Martin} }