Paper Group ANR 242
Detecting Ground Control Points via Convolutional Neural Network for Stereo Matching. Learning Model Predictive Control for iterative tasks. A Data-Driven Control Framework. Disjunctive Normal Level Set: An Efficient Parametric Implicit Method. Handwriting recognition using Cohort of LSTM and lexicon verification with extremely large lexicon. Asymp …
Detecting Ground Control Points via Convolutional Neural Network for Stereo Matching
| Title | Detecting Ground Control Points via Convolutional Neural Network for Stereo Matching |
| Authors | Zhun Zhong, Songzhi Su, Donglin Cao, Shaozi Li |
| Abstract | In this paper, we present a novel approach to detect ground control points (GCPs) for stereo matching problem. First of all, we train a convolutional neural network (CNN) on a large stereo set, and compute the matching confidence of each pixel by using the trained CNN model. Secondly, we present a ground control points selection scheme according to the maximum matching confidence of each pixel. Finally, the selected GCPs are used to refine the matching costs, and we apply the new matching costs to perform optimization with semi-global matching algorithm for improving the final disparity maps. We evaluate our approach on the KITTI 2012 stereo benchmark dataset. Our experiments show that the proposed approach significantly improves the accuracy of disparity maps. |
| Tasks | Stereo Matching, Stereo Matching Hand |
| Published | 2016-05-08 |
| URL | http://arxiv.org/abs/1605.02289v1 |
| http://arxiv.org/pdf/1605.02289v1.pdf | |
| PWC | https://paperswithcode.com/paper/detecting-ground-control-points-via |
| Repo | |
| Framework | |
Learning Model Predictive Control for iterative tasks. A Data-Driven Control Framework
| Title | Learning Model Predictive Control for iterative tasks. A Data-Driven Control Framework |
| Authors | Ugo Rosolia, Francesco Borrelli |
| Abstract | A Learning Model Predictive Controller (LMPC) for iterative tasks is presented. The controller is reference-free and is able to improve its performance by learning from previous iterations. A safe set and a terminal cost function are used in order to guarantee recursive feasibility and non-increasing performance at each iteration. The paper presents the control design approach, and shows how to recursively construct terminal set and terminal cost from state and input trajectories of previous iterations. Simulation results show the effectiveness of the proposed control logic. |
| Tasks | |
| Published | 2016-09-06 |
| URL | http://arxiv.org/abs/1609.01387v7 |
| http://arxiv.org/pdf/1609.01387v7.pdf | |
| PWC | https://paperswithcode.com/paper/learning-model-predictive-control-for-1 |
| Repo | |
| Framework | |
Disjunctive Normal Level Set: An Efficient Parametric Implicit Method
| Title | Disjunctive Normal Level Set: An Efficient Parametric Implicit Method |
| Authors | Fitsum Mesadi, Mujdat Cetin, Tolga Tasdizen |
| Abstract | Level set methods are widely used for image segmentation because of their capability to handle topological changes. In this paper, we propose a novel parametric level set method called Disjunctive Normal Level Set (DNLS), and apply it to both two phase (single object) and multiphase (multi-object) image segmentations. The DNLS is formed by union of polytopes which themselves are formed by intersections of half-spaces. The proposed level set framework has the following major advantages compared to other level set methods available in the literature. First, segmentation using DNLS converges much faster. Second, the DNLS level set function remains regular throughout its evolution. Third, the proposed multiphase version of the DNLS is less sensitive to initialization, and its computational cost and memory requirement remains almost constant as the number of objects to be simultaneously segmented grows. The experimental results show the potential of the proposed method. |
| Tasks | Semantic Segmentation |
| Published | 2016-06-24 |
| URL | http://arxiv.org/abs/1606.07511v1 |
| http://arxiv.org/pdf/1606.07511v1.pdf | |
| PWC | https://paperswithcode.com/paper/disjunctive-normal-level-set-an-efficient |
| Repo | |
| Framework | |
Handwriting recognition using Cohort of LSTM and lexicon verification with extremely large lexicon
| Title | Handwriting recognition using Cohort of LSTM and lexicon verification with extremely large lexicon |
| Authors | Bruno Stuner, Clément Chatelain, Thierry Paquet |
| Abstract | State-of-the-art methods for handwriting recognition are based on Long Short Term Memory (LSTM) recurrent neural networks (RNN), which now provides very impressive character recognition performance. The character recognition is generally coupled with a lexicon driven decoding process which integrates dictionaries. Unfortunately these dictionaries are limited to hundred of thousands words for the best systems, which prevent from having a good language coverage, and therefore limit the global recognition performance. In this article, we propose an alternative to the lexicon driven decoding process based on a lexicon verification process, coupled with an original cascade architecture. The cascade is made of a large number of complementary networks extracted from a single training (called cohort), making the learning process very light. The proposed method achieves new state-of-the art word recognition performance on the Rimes and IAM databases. Dealing with gigantic lexicon of 3 millions words, the methods also demonstrates interesting performance with a fast decision stage. |
| Tasks | |
| Published | 2016-12-22 |
| URL | http://arxiv.org/abs/1612.07528v4 |
| http://arxiv.org/pdf/1612.07528v4.pdf | |
| PWC | https://paperswithcode.com/paper/handwriting-recognition-using-cohort-of-lstm |
| Repo | |
| Framework | |
Asymptotic properties for combined $L_1$ and concave regularization
| Title | Asymptotic properties for combined $L_1$ and concave regularization |
| Authors | Yingying Fan, Jinchi Lv |
| Abstract | Two important goals of high-dimensional modeling are prediction and variable selection. In this article, we consider regularization with combined $L_1$ and concave penalties, and study the sampling properties of the global optimum of the suggested method in ultra-high dimensional settings. The $L_1$-penalty provides the minimum regularization needed for removing noise variables in order to achieve oracle prediction risk, while concave penalty imposes additional regularization to control model sparsity. In the linear model setting, we prove that the global optimum of our method enjoys the same oracle inequalities as the lasso estimator and admits an explicit bound on the false sign rate, which can be asymptotically vanishing. Moreover, we establish oracle risk inequalities for the method and the sampling properties of computable solutions. Numerical studies suggest that our method yields more stable estimates than using a concave penalty alone. |
| Tasks | |
| Published | 2016-05-11 |
| URL | http://arxiv.org/abs/1605.03335v1 |
| http://arxiv.org/pdf/1605.03335v1.pdf | |
| PWC | https://paperswithcode.com/paper/asymptotic-properties-for-combined-l_1-and |
| Repo | |
| Framework | |
Epipolar Geometry Based On Line Similarity
| Title | Epipolar Geometry Based On Line Similarity |
| Authors | Gil Ben-Artzi, Tavi Halperin, Michael Werman, Shmuel Peleg |
| Abstract | It is known that epipolar geometry can be computed from three epipolar line correspondences but this computation is rarely used in practice since there are no simple methods to find corresponding lines. Instead, methods for finding corresponding points are widely used. This paper proposes a similarity measure between lines that indicates whether two lines are corresponding epipolar lines and enables finding epipolar line correspondences as needed for the computation of epipolar geometry. A similarity measure between two lines, suitable for video sequences of a dynamic scene, has been previously described. This paper suggests a stereo matching similarity measure suitable for images. It is based on the quality of stereo matching between the two lines, as corresponding epipolar lines yield a good stereo correspondence. Instead of an exhaustive search over all possible pairs of lines, the search space is substantially reduced when two corresponding point pairs are given. We validate the proposed method using real-world images and compare it to state-of-the-art methods. We found this method to be more accurate by a factor of five compared to the standard method using seven corresponding points and comparable to the 8-points algorithm. |
| Tasks | Stereo Matching, Stereo Matching Hand |
| Published | 2016-04-17 |
| URL | http://arxiv.org/abs/1604.04848v4 |
| http://arxiv.org/pdf/1604.04848v4.pdf | |
| PWC | https://paperswithcode.com/paper/epipolar-geometry-based-on-line-similarity |
| Repo | |
| Framework | |
Improving Raw Image Storage Efficiency by Exploiting Similarity
| Title | Improving Raw Image Storage Efficiency by Exploiting Similarity |
| Authors | Binqi Zhang, Chen Wang, Bing Bing Zhou, Albert Y. Zomaya |
| Abstract | To improve the temporal and spatial storage efficiency, researchers have intensively studied various techniques, including compression and deduplication. Through our evaluation, we find that methods such as photo tags or local features help to identify the content-based similar- ity between raw images. The images can then be com- pressed more efficiently to get better storage space sav- ings. Furthermore, storing similar raw images together enables rapid data sorting, searching and retrieval if the images are stored in a distributed and large-scale envi- ronment by reducing fragmentation. In this paper, we evaluated the compressibility by designing experiments and observing the results. We found that on a statistical basis the higher similarity photos have, the better com- pression results are. This research helps provide a clue for future large-scale storage system design. |
| Tasks | |
| Published | 2016-04-19 |
| URL | http://arxiv.org/abs/1604.05442v1 |
| http://arxiv.org/pdf/1604.05442v1.pdf | |
| PWC | https://paperswithcode.com/paper/improving-raw-image-storage-efficiency-by |
| Repo | |
| Framework | |
Solving Dense Image Matching in Real-Time using Discrete-Continuous Optimization
| Title | Solving Dense Image Matching in Real-Time using Discrete-Continuous Optimization |
| Authors | Alexander Shekhovtsov, Christian Reinbacher, Gottfried Graber, Thomas Pock |
| Abstract | Dense image matching is a fundamental low-level problem in Computer Vision, which has received tremendous attention from both discrete and continuous optimization communities. The goal of this paper is to combine the advantages of discrete and continuous optimization in a coherent framework. We devise a model based on energy minimization, to be optimized by both discrete and continuous algorithms in a consistent way. In the discrete setting, we propose a novel optimization algorithm that can be massively parallelized. In the continuous setting we tackle the problem of non-convex regularizers by a formulation based on differences of convex functions. The resulting hybrid discrete-continuous algorithm can be efficiently accelerated by modern GPUs and we demonstrate its real-time performance for the applications of dense stereo matching and optical flow. |
| Tasks | Optical Flow Estimation, Stereo Matching, Stereo Matching Hand |
| Published | 2016-01-23 |
| URL | http://arxiv.org/abs/1601.06274v1 |
| http://arxiv.org/pdf/1601.06274v1.pdf | |
| PWC | https://paperswithcode.com/paper/solving-dense-image-matching-in-real-time |
| Repo | |
| Framework | |
Predicting User Roles in Social Networks using Transfer Learning with Feature Transformation
| Title | Predicting User Roles in Social Networks using Transfer Learning with Feature Transformation |
| Authors | Jun Sun, Jérôme Kunegis, Steffen Staab |
| Abstract | How can we recognise social roles of people, given a completely unlabelled social network? We present a transfer learning approach to network role classification based on feature transformations from each network’s local feature distribution to a global feature space. Experiments are carried out on real-world datasets. (See manuscript for the full abstract.) |
| Tasks | Transfer Learning |
| Published | 2016-11-09 |
| URL | http://arxiv.org/abs/1611.02941v1 |
| http://arxiv.org/pdf/1611.02941v1.pdf | |
| PWC | https://paperswithcode.com/paper/predicting-user-roles-in-social-networks |
| Repo | |
| Framework | |
A Closed-Form Solution to Tensor Voting: Theory and Applications
| Title | A Closed-Form Solution to Tensor Voting: Theory and Applications |
| Authors | Tai-Pang Wu, Sai-Kit Yeung, Jiaya Jia, Chi-Keung Tang, Gerard Medioni |
| Abstract | We prove a closed-form solution to tensor voting (CFTV): given a point set in any dimensions, our closed-form solution provides an exact, continuous and efficient algorithm for computing a structure-aware tensor that simultaneously achieves salient structure detection and outlier attenuation. Using CFTV, we prove the convergence of tensor voting on a Markov random field (MRF), thus termed as MRFTV, where the structure-aware tensor at each input site reaches a stationary state upon convergence in structure propagation. We then embed structure-aware tensor into expectation maximization (EM) for optimizing a single linear structure to achieve efficient and robust parameter estimation. Specifically, our EMTV algorithm optimizes both the tensor and fitting parameters and does not require random sampling consensus typically used in existing robust statistical techniques. We performed quantitative evaluation on its accuracy and robustness, showing that EMTV performs better than the original TV and other state-of-the-art techniques in fundamental matrix estimation for multiview stereo matching. The extensions of CFTV and EMTV for extracting multiple and nonlinear structures are underway. An addendum is included in this arXiv version. |
| Tasks | Stereo Matching, Stereo Matching Hand |
| Published | 2016-01-19 |
| URL | http://arxiv.org/abs/1601.04888v2 |
| http://arxiv.org/pdf/1601.04888v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-closed-form-solution-to-tensor-voting |
| Repo | |
| Framework | |
Stereo Matching by Joint Energy Minimization
| Title | Stereo Matching by Joint Energy Minimization |
| Authors | Hongyang Xue, Deng Cai |
| Abstract | In [18], Mozerov et al. propose to perform stereo matching as a two-step energy minimization problem. For the first step they solve a fully connected MRF model. And in the next step the marginal output is employed as the unary cost for a locally connected MRF model. In this paper we intend to combine the two steps of energy minimization in order to improve stereo matching results. We observe that the fully connected MRF leads to smoother disparity maps, while the locally connected MRF achieves superior results in fine-structured regions. Thus we propose to jointly solve the fully connected and locally connected models, taking both their advantages into account. The joint model is solved by mean field approximations. While remaining efficient, our joint model outperforms the two-step energy minimization approach in both time and estimation error on the Middlebury stereo benchmark v3. |
| Tasks | Stereo Matching, Stereo Matching Hand |
| Published | 2016-01-15 |
| URL | http://arxiv.org/abs/1601.03890v3 |
| http://arxiv.org/pdf/1601.03890v3.pdf | |
| PWC | https://paperswithcode.com/paper/stereo-matching-by-joint-energy-minimization |
| Repo | |
| Framework | |
Probabilistic Duality for Parallel Gibbs Sampling without Graph Coloring
| Title | Probabilistic Duality for Parallel Gibbs Sampling without Graph Coloring |
| Authors | Lars Mescheder, Sebastian Nowozin, Andreas Geiger |
| Abstract | We present a new notion of probabilistic duality for random variables involving mixture distributions. Using this notion, we show how to implement a highly-parallelizable Gibbs sampler for weakly coupled discrete pairwise graphical models with strictly positive factors that requires almost no preprocessing and is easy to implement. Moreover, we show how our method can be combined with blocking to improve mixing. Even though our method leads to inferior mixing times compared to a sequential Gibbs sampler, we argue that our method is still very useful for large dynamic networks, where factors are added and removed on a continuous basis, as it is hard to maintain a graph coloring in this setup. Similarly, our method is useful for parallelizing Gibbs sampling in graphical models that do not allow for graph colorings with a small number of colors such as densely connected graphs. |
| Tasks | |
| Published | 2016-11-21 |
| URL | http://arxiv.org/abs/1611.06684v1 |
| http://arxiv.org/pdf/1611.06684v1.pdf | |
| PWC | https://paperswithcode.com/paper/probabilistic-duality-for-parallel-gibbs |
| Repo | |
| Framework | |
ActiveClean: Interactive Data Cleaning While Learning Convex Loss Models
| Title | ActiveClean: Interactive Data Cleaning While Learning Convex Loss Models |
| Authors | Sanjay Krishnan, Jiannan Wang, Eugene Wu, Michael J. Franklin, Ken Goldberg |
| Abstract | Data cleaning is often an important step to ensure that predictive models, such as regression and classification, are not affected by systematic errors such as inconsistent, out-of-date, or outlier data. Identifying dirty data is often a manual and iterative process, and can be challenging on large datasets. However, many data cleaning workflows can introduce subtle biases into the training processes due to violation of independence assumptions. We propose ActiveClean, a progressive cleaning approach where the model is updated incrementally instead of re-training and can guarantee accuracy on partially cleaned data. ActiveClean supports a popular class of models called convex loss models (e.g., linear regression and SVMs). ActiveClean also leverages the structure of a user’s model to prioritize cleaning those records likely to affect the results. We evaluate ActiveClean on five real-world datasets UCI Adult, UCI EEG, MNIST, Dollars For Docs, and WorldBank with both real and synthetic errors. Our results suggest that our proposed optimizations can improve model accuracy by up-to 2.5x for the same amount of data cleaned. Furthermore for a fixed cleaning budget and on all real dirty datasets, ActiveClean returns more accurate models than uniform sampling and Active Learning. |
| Tasks | Active Learning, EEG |
| Published | 2016-01-15 |
| URL | http://arxiv.org/abs/1601.03797v1 |
| http://arxiv.org/pdf/1601.03797v1.pdf | |
| PWC | https://paperswithcode.com/paper/activeclean-interactive-data-cleaning-while |
| Repo | |
| Framework | |
Domain knowledge assisted cyst segmentation in OCT retinal images
| Title | Domain knowledge assisted cyst segmentation in OCT retinal images |
| Authors | Karthik Gopinath, Jayanthi Sivaswamy |
| Abstract | 3D imaging modalities are becoming increasingly popular and relevant in retinal imaging owing to their effectiveness in highlighting structures in sub-retinal layers. OCT is one such modality which has great importance in the context of analysis of cystoid structures in subretinal layers. Signal to noise ratio(SNR) of the images obtained from OCT is less and hence automated and accurate determination of cystoid structures from OCT is a challenging task. We propose an automated method for detecting/segmenting cysts in 3D OCT volumes. The proposed method is biologically inspired and fast aided by the domain knowledge about the cystoid structures. An ensemble learning methodRandom forests is learnt for classification of detected region into cyst region. The method achieves detection and segmentation in a unified setting. We believe the proposed approach with further improvements can be a promising starting point for more robust approach. This method is validated against the training set achieves a mean dice coefficient of 0.3893 with a standard deviation of 0.2987 |
| Tasks | |
| Published | 2016-12-08 |
| URL | http://arxiv.org/abs/1612.02675v1 |
| http://arxiv.org/pdf/1612.02675v1.pdf | |
| PWC | https://paperswithcode.com/paper/domain-knowledge-assisted-cyst-segmentation |
| Repo | |
| Framework | |
Personalized Advertisement Recommendation: A Ranking Approach to Address the Ubiquitous Click Sparsity Problem
| Title | Personalized Advertisement Recommendation: A Ranking Approach to Address the Ubiquitous Click Sparsity Problem |
| Authors | Sougata Chaudhuri, Georgios Theocharous, Mohammad Ghavamzadeh |
| Abstract | We study the problem of personalized advertisement recommendation (PAR), which consist of a user visiting a system (website) and the system displaying one of $K$ ads to the user. The system uses an internal ad recommendation policy to map the user’s profile (context) to one of the ads. The user either clicks or ignores the ad and correspondingly, the system updates its recommendation policy. PAR problem is usually tackled by scalable \emph{contextual bandit} algorithms, where the policies are generally based on classifiers. A practical problem in PAR is extreme click sparsity, due to very few users actually clicking on ads. We systematically study the drawback of using contextual bandit algorithms based on classifier-based policies, in face of extreme click sparsity. We then suggest an alternate policy, based on rankers, learnt by optimizing the Area Under the Curve (AUC) ranking loss, which can significantly alleviate the problem of click sparsity. We conduct extensive experiments on public datasets, as well as three industry proprietary datasets, to illustrate the improvement in click-through-rate (CTR) obtained by using the ranker-based policy over classifier-based policies. |
| Tasks | |
| Published | 2016-03-06 |
| URL | http://arxiv.org/abs/1603.01870v1 |
| http://arxiv.org/pdf/1603.01870v1.pdf | |
| PWC | https://paperswithcode.com/paper/personalized-advertisement-recommendation-a |
| Repo | |
| Framework | |
