Paper Group ANR 83
Deformable Shape Completion with Graph Convolutional Autoencoders. Guiding Reinforcement Learning Exploration Using Natural Language. Evidence of an exponential speed-up in the solution of hard optimization problems. Multiframe Scene Flow with Piecewise Rigid Motion. Perivascular Spaces Segmentation in Brain MRI Using Optimal 3D Filtering. Learning …
Deformable Shape Completion with Graph Convolutional Autoencoders
| Title | Deformable Shape Completion with Graph Convolutional Autoencoders |
| Authors | Or Litany, Alex Bronstein, Michael Bronstein, Ameesh Makadia |
| Abstract | The availability of affordable and portable depth sensors has made scanning objects and people simpler than ever. However, dealing with occlusions and missing parts is still a significant challenge. The problem of reconstructing a (possibly non-rigidly moving) 3D object from a single or multiple partial scans has received increasing attention in recent years. In this work, we propose a novel learning-based method for the completion of partial shapes. Unlike the majority of existing approaches, our method focuses on objects that can undergo non-rigid deformations. The core of our method is a variational autoencoder with graph convolutional operations that learns a latent space for complete realistic shapes. At inference, we optimize to find the representation in this latent space that best fits the generated shape to the known partial input. The completed shape exhibits a realistic appearance on the unknown part. We show promising results towards the completion of synthetic and real scans of human body and face meshes exhibiting different styles of articulation and partiality. |
| Tasks | |
| Published | 2017-12-01 |
| URL | http://arxiv.org/abs/1712.00268v4 |
| http://arxiv.org/pdf/1712.00268v4.pdf | |
| PWC | https://paperswithcode.com/paper/deformable-shape-completion-with-graph |
| Repo | |
| Framework | |
Guiding Reinforcement Learning Exploration Using Natural Language
| Title | Guiding Reinforcement Learning Exploration Using Natural Language |
| Authors | Brent Harrison, Upol Ehsan, Mark O. Riedl |
| Abstract | In this work we present a technique to use natural language to help reinforcement learning generalize to unseen environments. This technique uses neural machine translation, specifically the use of encoder-decoder networks, to learn associations between natural language behavior descriptions and state-action information. We then use this learned model to guide agent exploration using a modified version of policy shaping to make it more effective at learning in unseen environments. We evaluate this technique using the popular arcade game, Frogger, under ideal and non-ideal conditions. This evaluation shows that our modified policy shaping algorithm improves over a Q-learning agent as well as a baseline version of policy shaping. |
| Tasks | Machine Translation, Q-Learning |
| Published | 2017-07-26 |
| URL | http://arxiv.org/abs/1707.08616v2 |
| http://arxiv.org/pdf/1707.08616v2.pdf | |
| PWC | https://paperswithcode.com/paper/guiding-reinforcement-learning-exploration |
| Repo | |
| Framework | |
Evidence of an exponential speed-up in the solution of hard optimization problems
| Title | Evidence of an exponential speed-up in the solution of hard optimization problems |
| Authors | Fabio L. Traversa, Pietro Cicotti, Forrest Sheldon, Massimiliano Di Ventra |
| Abstract | Optimization problems pervade essentially every scientific discipline and industry. Many such problems require finding a solution that maximizes the number of constraints satisfied. Often, these problems are particularly difficult to solve because they belong to the NP-hard class, namely algorithms that always find a solution in polynomial time are not known. Over the past decades, research has focused on developing heuristic approaches that attempt to find an approximation to the solution. However, despite numerous research efforts, in many cases even approximations to the optimal solution are hard to find, as the computational time for further refining a candidate solution grows exponentially with input size. Here, we show a non-combinatorial approach to hard optimization problems that achieves an exponential speed-up and finds better approximations than the current state-of-the-art. First, we map the optimization problem into a boolean circuit made of specially designed, self-organizing logic gates, which can be built with (non-quantum) electronic components; the equilibrium points of the circuit represent the approximation to the problem at hand. Then, we solve its associated non-linear ordinary differential equations numerically, towards the equilibrium points. We demonstrate this exponential gain by comparing a sequential MatLab implementation of our solver with the winners of the 2016 Max-SAT competition on a variety of hard optimization instances. We show empirical evidence that our solver scales linearly with the size of the problem, both in time and memory, and argue that this property derives from the collective behavior of the simulated physical circuit. Our approach can be applied to other types of optimization problems and the results presented here have far-reaching consequences in many fields. |
| Tasks | |
| Published | 2017-10-23 |
| URL | http://arxiv.org/abs/1710.09278v1 |
| http://arxiv.org/pdf/1710.09278v1.pdf | |
| PWC | https://paperswithcode.com/paper/evidence-of-an-exponential-speed-up-in-the |
| Repo | |
| Framework | |
Multiframe Scene Flow with Piecewise Rigid Motion
| Title | Multiframe Scene Flow with Piecewise Rigid Motion |
| Authors | Vladislav Golyanik, Kihwan Kim, Robert Maier, Matthias Nießner, Didier Stricker, Jan Kautz |
| Abstract | We introduce a novel multiframe scene flow approach that jointly optimizes the consistency of the patch appearances and their local rigid motions from RGB-D image sequences. In contrast to the competing methods, we take advantage of an oversegmentation of the reference frame and robust optimization techniques. We formulate scene flow recovery as a global non-linear least squares problem which is iteratively solved by a damped Gauss-Newton approach. As a result, we obtain a qualitatively new level of accuracy in RGB-D based scene flow estimation which can potentially run in real-time. Our method can handle challenging cases with rigid, piecewise rigid, articulated and moderate non-rigid motion, and does not rely on prior knowledge about the types of motions and deformations. Extensive experiments on synthetic and real data show that our method outperforms state-of-the-art. |
| Tasks | Scene Flow Estimation |
| Published | 2017-10-05 |
| URL | http://arxiv.org/abs/1710.02124v1 |
| http://arxiv.org/pdf/1710.02124v1.pdf | |
| PWC | https://paperswithcode.com/paper/multiframe-scene-flow-with-piecewise-rigid |
| Repo | |
| Framework | |
Perivascular Spaces Segmentation in Brain MRI Using Optimal 3D Filtering
| Title | Perivascular Spaces Segmentation in Brain MRI Using Optimal 3D Filtering |
| Authors | Lucia Ballerini, Ruggiero Lovreglio, Maria del C. Valdes-Hernandez, Joel Ramirez, Bradley J. MacIntosh, Sandra E. Black, Joanna M. Wardlaw |
| Abstract | Perivascular Spaces (PVS) are a recently recognised feature of Small Vessel Disease (SVD), also indicating neuroinflammation, and are an important part of the brain’s circulation and glymphatic drainage system. Quantitative analysis of PVS on Magnetic Resonance Images (MRI) is important for understanding their relationship with neurological diseases. In this work, we propose a segmentation technique based on the 3D Frangi filtering for extraction of PVS from MRI. Based on prior knowledge from neuroradiological ratings of PVS, we used ordered logit models to optimise Frangi filter parameters in response to the variability in the scanner’s parameters and study protocols. We optimized and validated our proposed models on two independent cohorts, a dementia sample (N=20) and patients who previously had mild to moderate stroke (N=48). Results demonstrate the robustness and generalisability of our segmentation method. Segmentation-based PVS burden estimates correlated with neuroradiological assessments (Spearman’s $\rho$ = 0.74, p $<$ 0.001), suggesting the great potential of our proposed method |
| Tasks | |
| Published | 2017-04-25 |
| URL | http://arxiv.org/abs/1704.07699v1 |
| http://arxiv.org/pdf/1704.07699v1.pdf | |
| PWC | https://paperswithcode.com/paper/perivascular-spaces-segmentation-in-brain-mri |
| Repo | |
| Framework | |
Learning to Match
| Title | Learning to Match |
| Authors | Philip Ekman, Sebastian Bellevik, Christos Dimitrakakis, Aristide Tossou |
| Abstract | Outsourcing tasks to previously unknown parties is becoming more common. One specific such problem involves matching a set of workers to a set of tasks. Even if the latter have precise requirements, the quality of individual workers is usually unknown. The problem is thus a version of matching under uncertainty. We believe that this type of problem is going to be increasingly important. When the problem involves only a single skill or type of job, it is essentially a type of bandit problem, and can be solved with standard algorithms. However, we develop an algorithm that can perform matching for workers with multiple skills hired for multiple jobs with multiple requirements. We perform an experimental evaluation in both single-task and multi-task problems, comparing with the bounded $\epsilon$-first algorithm, as well as an oracle that knows the true skills of workers. One of the algorithms we developed gives results approaching 85% of oracle’s performance. We invite the community to take a closer look at this problem and develop real-world benchmarks. |
| Tasks | |
| Published | 2017-07-30 |
| URL | http://arxiv.org/abs/1707.09678v1 |
| http://arxiv.org/pdf/1707.09678v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-to-match |
| Repo | |
| Framework | |
Online Dynamic Programming
| Title | Online Dynamic Programming |
| Authors | Holakou Rahmanian, Manfred K. Warmuth |
| Abstract | We consider the problem of repeatedly solving a variant of the same dynamic programming problem in successive trials. An instance of the type of problems we consider is to find a good binary search tree in a changing environment.At the beginning of each trial, the learner probabilistically chooses a tree with the $n$ keys at the internal nodes and the $n+1$ gaps between keys at the leaves. The learner is then told the frequencies of the keys and gaps and is charged by the average search cost for the chosen tree. The problem is online because the frequencies can change between trials. The goal is to develop algorithms with the property that their total average search cost (loss) in all trials is close to the total loss of the best tree chosen in hindsight for all trials. The challenge, of course, is that the algorithm has to deal with exponential number of trees. We develop a general methodology for tackling such problems for a wide class of dynamic programming algorithms. Our framework allows us to extend online learning algorithms like Hedge and Component Hedge to a significantly wider class of combinatorial objects than was possible before. |
| Tasks | |
| Published | 2017-06-02 |
| URL | http://arxiv.org/abs/1706.00834v3 |
| http://arxiv.org/pdf/1706.00834v3.pdf | |
| PWC | https://paperswithcode.com/paper/online-dynamic-programming |
| Repo | |
| Framework | |
Combinatorial Multi-armed Bandit with Probabilistically Triggered Arms: A Case with Bounded Regret
| Title | Combinatorial Multi-armed Bandit with Probabilistically Triggered Arms: A Case with Bounded Regret |
| Authors | A. Ömer Sarıtaç, Cem Tekin |
| Abstract | In this paper, we study the combinatorial multi-armed bandit problem (CMAB) with probabilistically triggered arms (PTAs). Under the assumption that the arm triggering probabilities (ATPs) are positive for all arms, we prove that a class of upper confidence bound (UCB) policies, named Combinatorial UCB with exploration rate $\kappa$ (CUCB-$\kappa$), and Combinatorial Thompson Sampling (CTS), which estimates the expected states of the arms via Thompson sampling, achieve bounded regret. In addition, we prove that CUCB-$0$ and CTS incur $O(\sqrt{T})$ gap-independent regret. These results improve the results in previous works, which show $O(\log T)$ gap-dependent and $O(\sqrt{T\log T})$ gap-independent regrets, respectively, under no assumptions on the ATPs. Then, we numerically evaluate the performance of CUCB-$\kappa$ and CTS in a real-world movie recommendation problem, where the actions correspond to recommending a set of movies, the arms correspond to the edges between the movies and the users, and the goal is to maximize the total number of users that are attracted by at least one movie. Our numerical results complement our theoretical findings on bounded regret. Apart from this problem, our results also directly apply to the online influence maximization (OIM) problem studied in numerous prior works. |
| Tasks | |
| Published | 2017-07-24 |
| URL | http://arxiv.org/abs/1707.07443v1 |
| http://arxiv.org/pdf/1707.07443v1.pdf | |
| PWC | https://paperswithcode.com/paper/combinatorial-multi-armed-bandit-with |
| Repo | |
| Framework | |
Joint Multi-view Face Alignment in the Wild
| Title | Joint Multi-view Face Alignment in the Wild |
| Authors | Jiankang Deng, George Trigeorgis, Yuxiang Zhou, Stefanos Zafeiriou |
| Abstract | The de facto algorithm for facial landmark estimation involves running a face detector with a subsequent deformable model fitting on the bounding box. This encompasses two basic problems: i) the detection and deformable fitting steps are performed independently, while the detector might not provide best-suited initialisation for the fitting step, ii) the face appearance varies hugely across different poses, which makes the deformable face fitting very challenging and thus distinct models have to be used (\eg, one for profile and one for frontal faces). In this work, we propose the first, to the best of our knowledge, joint multi-view convolutional network to handle large pose variations across faces in-the-wild, and elegantly bridge face detection and facial landmark localisation tasks. Existing joint face detection and landmark localisation methods focus only on a very small set of landmarks. By contrast, our method can detect and align a large number of landmarks for semi-frontal (68 landmarks) and profile (39 landmarks) faces. We evaluate our model on a plethora of datasets including standard static image datasets such as IBUG, 300W, COFW, and the latest Menpo Benchmark for both semi-frontal and profile faces. Significant improvement over state-of-the-art methods on deformable face tracking is witnessed on 300VW benchmark. We also demonstrate state-of-the-art results for face detection on FDDB and MALF datasets. |
| Tasks | Face Alignment, Face Detection |
| Published | 2017-08-20 |
| URL | http://arxiv.org/abs/1708.06023v1 |
| http://arxiv.org/pdf/1708.06023v1.pdf | |
| PWC | https://paperswithcode.com/paper/joint-multi-view-face-alignment-in-the-wild |
| Repo | |
| Framework | |
Automatic Liver Segmentation Using an Adversarial Image-to-Image Network
| Title | Automatic Liver Segmentation Using an Adversarial Image-to-Image Network |
| Authors | Dong Yang, Daguang Xu, S. Kevin Zhou, Bogdan Georgescu, Mingqing Chen, Sasa Grbic, Dimitris Metaxas, Dorin Comaniciu |
| Abstract | Automatic liver segmentation in 3D medical images is essential in many clinical applications, such as pathological diagnosis of hepatic diseases, surgical planning, and postoperative assessment. However, it is still a very challenging task due to the complex background, fuzzy boundary, and various appearance of liver. In this paper, we propose an automatic and efficient algorithm to segment liver from 3D CT volumes. A deep image-to-image network (DI2IN) is first deployed to generate the liver segmentation, employing a convolutional encoder-decoder architecture combined with multi-level feature concatenation and deep supervision. Then an adversarial network is utilized during training process to discriminate the output of DI2IN from ground truth, which further boosts the performance of DI2IN. The proposed method is trained on an annotated dataset of 1000 CT volumes with various different scanning protocols (e.g., contrast and non-contrast, various resolution and position) and large variations in populations (e.g., ages and pathology). Our approach outperforms the state-of-the-art solutions in terms of segmentation accuracy and computing efficiency. |
| Tasks | Liver Segmentation |
| Published | 2017-07-25 |
| URL | http://arxiv.org/abs/1707.08037v1 |
| http://arxiv.org/pdf/1707.08037v1.pdf | |
| PWC | https://paperswithcode.com/paper/automatic-liver-segmentation-using-an |
| Repo | |
| Framework | |
Deep Face Feature for Face Alignment
| Title | Deep Face Feature for Face Alignment |
| Authors | Boyi Jiang, Juyong Zhang, Bailin Deng, Yudong Guo, Ligang Liu |
| Abstract | In this paper, we present a deep learning based image feature extraction method designed specifically for face images. To train the feature extraction model, we construct a large scale photo-realistic face image dataset with ground-truth correspondence between multi-view face images, which are synthesized from real photographs via an inverse rendering procedure. The deep face feature (DFF) is trained using correspondence between face images rendered from different views. Using the trained DFF model, we can extract a feature vector for each pixel of a face image, which distinguishes different facial regions and is shown to be more effective than general-purpose feature descriptors for face-related tasks such as matching and alignment. Based on the DFF, we develop a robust face alignment method, which iteratively updates landmarks, pose and 3D shape. Extensive experiments demonstrate that our method can achieve state-of-the-art results for face alignment under highly unconstrained face images. |
| Tasks | Face Alignment, Robust Face Alignment |
| Published | 2017-08-09 |
| URL | http://arxiv.org/abs/1708.02721v2 |
| http://arxiv.org/pdf/1708.02721v2.pdf | |
| PWC | https://paperswithcode.com/paper/deep-face-feature-for-face-alignment |
| Repo | |
| Framework | |
Joint Face Alignment and 3D Face Reconstruction with Application to Face Recognition
| Title | Joint Face Alignment and 3D Face Reconstruction with Application to Face Recognition |
| Authors | Feng Liu, Qijun Zhao, Xiaoming Liu, Dan Zeng |
| Abstract | Face alignment and 3D face reconstruction are traditionally accomplished as separated tasks. By exploring the strong correlation between 2D landmarks and 3D shapes, in contrast, we propose a joint face alignment and 3D face reconstruction method to simultaneously solve these two problems for 2D face images of arbitrary poses and expressions. This method, based on a summation model of 3D faces and cascaded regression in 2D and 3D shape spaces, iteratively and alternately applies two cascaded regressors, one for updating 2D landmarks and the other for 3D shape. The 3D shape and the landmarks are correlated via a 3D-to-2D mapping matrix, which is updated in each iteration to refine the location and visibility of 2D landmarks. Unlike existing methods, the proposed method can fully automatically generate both pose-and-expression-normalized (PEN) and expressive 3D faces and localize both visible and invisible 2D landmarks. Based on the PEN 3D faces, we devise a method to enhance face recognition accuracy across poses and expressions. Both linear and nonlinear implementations of the proposed method are presented and evaluated in this paper. Extensive experiments show that the proposed method can achieve the state-of-the-art accuracy in both face alignment and 3D face reconstruction, and benefit face recognition owing to its reconstructed PEN 3D face. |
| Tasks | 3D Face Reconstruction, Face Alignment, Face Recognition, Face Reconstruction |
| Published | 2017-08-09 |
| URL | http://arxiv.org/abs/1708.02734v2 |
| http://arxiv.org/pdf/1708.02734v2.pdf | |
| PWC | https://paperswithcode.com/paper/joint-face-alignment-and-3d-face |
| Repo | |
| Framework | |
GRASS: Generative Recursive Autoencoders for Shape Structures
| Title | GRASS: Generative Recursive Autoencoders for Shape Structures |
| Authors | Jun Li, Kai Xu, Siddhartha Chaudhuri, Ersin Yumer, Hao Zhang, Leonidas Guibas |
| Abstract | We introduce a novel neural network architecture for encoding and synthesis of 3D shapes, particularly their structures. Our key insight is that 3D shapes are effectively characterized by their hierarchical organization of parts, which reflects fundamental intra-shape relationships such as adjacency and symmetry. We develop a recursive neural net (RvNN) based autoencoder to map a flat, unlabeled, arbitrary part layout to a compact code. The code effectively captures hierarchical structures of man-made 3D objects of varying structural complexities despite being fixed-dimensional: an associated decoder maps a code back to a full hierarchy. The learned bidirectional mapping is further tuned using an adversarial setup to yield a generative model of plausible structures, from which novel structures can be sampled. Finally, our structure synthesis framework is augmented by a second trained module that produces fine-grained part geometry, conditioned on global and local structural context, leading to a full generative pipeline for 3D shapes. We demonstrate that without supervision, our network learns meaningful structural hierarchies adhering to perceptual grouping principles, produces compact codes which enable applications such as shape classification and partial matching, and supports shape synthesis and interpolation with significant variations in topology and geometry. |
| Tasks | |
| Published | 2017-05-05 |
| URL | http://arxiv.org/abs/1705.02090v2 |
| http://arxiv.org/pdf/1705.02090v2.pdf | |
| PWC | https://paperswithcode.com/paper/grass-generative-recursive-autoencoders-for |
| Repo | |
| Framework | |
Face Alignment Robust to Pose, Expressions and Occlusions
| Title | Face Alignment Robust to Pose, Expressions and Occlusions |
| Authors | Vishnu Naresh Boddeti, Myung-Cheol Roh, Jongju Shin, Takaharu Oguri, Takeo Kanade |
| Abstract | We propose an Ensemble of Robust Constrained Local Models for alignment of faces in the presence of significant occlusions and of any unknown pose and expression. To account for partial occlusions we introduce, Robust Constrained Local Models, that comprises of a deformable shape and local landmark appearance model and reasons over binary occlusion labels. Our occlusion reasoning proceeds by a hypothesize-and-test search over occlusion labels. Hypotheses are generated by Constrained Local Model based shape fitting over randomly sampled subsets of landmark detector responses and are evaluated by the quality of face alignment. To span the entire range of facial pose and expression variations we adopt an ensemble of independent Robust Constrained Local Models to search over a discretized representation of pose and expression. We perform extensive evaluation on a large number of face images, both occluded and unoccluded. We find that our face alignment system trained entirely on facial images captured “in-the-lab” exhibits a high degree of generalization to facial images captured “in-the-wild”. Our results are accurate and stable over a wide spectrum of occlusions, pose and expression variations resulting in excellent performance on many real-world face datasets. |
| Tasks | Face Alignment |
| Published | 2017-07-19 |
| URL | http://arxiv.org/abs/1707.05938v1 |
| http://arxiv.org/pdf/1707.05938v1.pdf | |
| PWC | https://paperswithcode.com/paper/face-alignment-robust-to-pose-expressions-and |
| Repo | |
| Framework | |
Attribute CNNs for Word Spotting in Handwritten Documents
| Title | Attribute CNNs for Word Spotting in Handwritten Documents |
| Authors | Sebastian Sudholt, Gernot Fink |
| Abstract | Word spotting has become a field of strong research interest in document image analysis over the last years. Recently, AttributeSVMs were proposed which predict a binary attribute representation. At their time, this influential method defined the state-of-the-art in segmentation-based word spotting. In this work, we present an approach for learning attribute representations with Convolutional Neural Networks (CNNs). By taking a probabilistic perspective on training CNNs, we derive two different loss functions for binary and real-valued word string embeddings. In addition, we propose two different CNN architectures, specifically designed for word spotting. These architectures are able to be trained in an end-to-end fashion. In a number of experiments, we investigate the influence of different word string embeddings and optimization strategies. We show our Attribute CNNs to achieve state-of-the-art results for segmentation-based word spotting on a large variety of data sets. |
| Tasks | Word Spotting In Handwritten Documents |
| Published | 2017-12-20 |
| URL | http://arxiv.org/abs/1712.07487v1 |
| http://arxiv.org/pdf/1712.07487v1.pdf | |
| PWC | https://paperswithcode.com/paper/attribute-cnns-for-word-spotting-in |
| Repo | |
| Framework | |
