Paper Group ANR 204
Scalable Gaussian Processes on Discrete Domains. Temporal Answer Set Programming on Finite Traces. On Meta-Learning for Dynamic Ensemble Selection. Structure-Aware 3D Hourglass Network for Hand Pose Estimation from Single Depth Image. Second-Order Asymptotically Optimal Statistical Classification. LineNet: a Zoomable CNN for Crowdsourced High Defin …
Scalable Gaussian Processes on Discrete Domains
| Title | Scalable Gaussian Processes on Discrete Domains |
| Authors | Vincent Fortuin, Gideon Dresdner, Heiko Strathmann, Gunnar Rätsch |
| Abstract | Kernel methods on discrete domains have shown great promise for many challenging data types, for instance, biological sequence data and molecular structure data. Scalable kernel methods like Support Vector Machines may offer good predictive performances but do not intrinsically provide uncertainty estimates. In contrast, probabilistic kernel methods like Gaussian Processes offer uncertainty estimates in addition to good predictive performance but fall short in terms of scalability. We present the first sparse Gaussian Process approximation framework on discrete input domains. Our framework achieves good predictive performance as well as uncertainty estimates using discrete optimization techniques. We present competitive results comparing our framework to baseline methods such as Support Vector Machines and full Gaussian Processes on synthetic data as well as on challenging real-world DNA sequence data. |
| Tasks | Gaussian Processes |
| Published | 2018-10-24 |
| URL | http://arxiv.org/abs/1810.10368v2 |
| http://arxiv.org/pdf/1810.10368v2.pdf | |
| PWC | https://paperswithcode.com/paper/scalable-gaussian-processes-on-discrete |
| Repo | |
| Framework | |
Temporal Answer Set Programming on Finite Traces
| Title | Temporal Answer Set Programming on Finite Traces |
| Authors | Pedro Cabalar, Roland Kaminski, Torsten Schaub, Anna Schuhmann |
| Abstract | In this paper, we introduce an alternative approach to Temporal Answer Set Programming that relies on a variation of Temporal Equilibrium Logic (TEL) for finite traces. This approach allows us to even out the expressiveness of TEL over infinite traces with the computational capacity of (incremental) Answer Set Programming (ASP). Also, we argue that finite traces are more natural when reasoning about action and change. As a result, our approach is readily implementable via multi-shot ASP systems and benefits from an extension of ASP’s full-fledged input language with temporal operators. This includes future as well as past operators whose combination offers a rich temporal modeling language. For computation, we identify the class of temporal logic programs and prove that it constitutes a normal form for our approach. Finally, we outline two implementations, a generic one and an extension of clingo. |
| Tasks | |
| Published | 2018-04-26 |
| URL | http://arxiv.org/abs/1804.10227v1 |
| http://arxiv.org/pdf/1804.10227v1.pdf | |
| PWC | https://paperswithcode.com/paper/temporal-answer-set-programming-on-finite |
| Repo | |
| Framework | |
On Meta-Learning for Dynamic Ensemble Selection
| Title | On Meta-Learning for Dynamic Ensemble Selection |
| Authors | Rafael M. O. Cruz, Robert Sabourin, George D. C. Cavalcanti |
| Abstract | In this paper, we propose a novel dynamic ensemble selection framework using meta-learning. The framework is divided into three steps. In the first step, the pool of classifiers is generated from the training data. The second phase is responsible to extract the meta-features and train the meta-classifier. Five distinct sets of meta-features are proposed, each one corresponding to a different criterion to measure the level of competence of a classifier for the classification of a given query sample. The meta-features are computed using the training data and used to train a meta-classifier that is able to predict whether or not a base classifier from the pool is competent enough to classify an input instance. Three different training scenarios for the training of the meta-classifier are considered: problem-dependent, problem-independent and hybrid. Experimental results show that the problem-dependent scenario provides the best result. In addition, the performance of the problem-dependent scenario is strongly correlated with the recognition rate of the system. A comparison with state-of-the-art techniques shows that the proposed-dependent approach outperforms current dynamic ensemble selection techniques. |
| Tasks | Meta-Learning |
| Published | 2018-11-01 |
| URL | http://arxiv.org/abs/1811.01743v1 |
| http://arxiv.org/pdf/1811.01743v1.pdf | |
| PWC | https://paperswithcode.com/paper/on-meta-learning-for-dynamic-ensemble |
| Repo | |
| Framework | |
Structure-Aware 3D Hourglass Network for Hand Pose Estimation from Single Depth Image
| Title | Structure-Aware 3D Hourglass Network for Hand Pose Estimation from Single Depth Image |
| Authors | Fuyang Huang, Ailing Zeng, Minhao Liu, Jing Qin, Qiang Xu |
| Abstract | In this paper, we propose a novel structure-aware 3D hourglass network for hand pose estimation from a single depth image, which achieves state-of-the-art results on MSRA and NYU datasets. Compared to existing works that perform image-to-coordination regression, our network takes 3D voxel as input and directly regresses 3D heatmap for each joint. To be specific, we use hourglass network as our backbone network and modify it into 3D form. We explicitly model tree-like finger bone into the network as well as in the loss function in an end-to-end manner, in order to take the skeleton constraints into consideration. Final estimation can then be easily obtained from voxel density map with simple post-processing. Experimental results show that the proposed structure-aware 3D hourglass network is able to achieve a mean joint error of 7.4 mm in MSRA and 8.9 mm in NYU datasets, respectively. |
| Tasks | Hand Pose Estimation, Pose Estimation |
| Published | 2018-12-26 |
| URL | http://arxiv.org/abs/1812.10320v1 |
| http://arxiv.org/pdf/1812.10320v1.pdf | |
| PWC | https://paperswithcode.com/paper/structure-aware-3d-hourglass-network-for-hand |
| Repo | |
| Framework | |
Second-Order Asymptotically Optimal Statistical Classification
| Title | Second-Order Asymptotically Optimal Statistical Classification |
| Authors | Lin Zhou, Vincent Y. F. Tan, Mehul Motani |
| Abstract | Motivated by real-world machine learning applications, we analyze approximations to the non-asymptotic fundamental limits of statistical classification. In the binary version of this problem, given two training sequences generated according to two {\em unknown} distributions $P_1$ and $P_2$, one is tasked to classify a test sequence which is known to be generated according to either $P_1$ or $P_2$. This problem can be thought of as an analogue of the binary hypothesis testing problem but in the present setting, the generating distributions are unknown. Due to finite sample considerations, we consider the second-order asymptotics (or dispersion-type) tradeoff between type-I and type-II error probabilities for tests which ensure that (i) the type-I error probability for {\em all} pairs of distributions decays exponentially fast and (ii) the type-II error probability for a {\em particular} pair of distributions is non-vanishing. We generalize our results to classification of multiple hypotheses with the rejection option. |
| Tasks | |
| Published | 2018-06-03 |
| URL | http://arxiv.org/abs/1806.00739v3 |
| http://arxiv.org/pdf/1806.00739v3.pdf | |
| PWC | https://paperswithcode.com/paper/second-order-asymptotically-optimal |
| Repo | |
| Framework | |
LineNet: a Zoomable CNN for Crowdsourced High Definition Maps Modeling in Urban Environments
| Title | LineNet: a Zoomable CNN for Crowdsourced High Definition Maps Modeling in Urban Environments |
| Authors | Dun Liang, Yuanchen Guo, Shaokui Zhang, Song-Hai Zhang, Peter Hall, Min Zhang, Shimin Hu |
| Abstract | High Definition (HD) maps play an important role in modern traffic scenes. However, the development of HD maps coverage grows slowly because of the cost limitation. To efficiently model HD maps, we proposed a convolutional neural network with a novel prediction layer and a zoom module, called LineNet. It is designed for state-of-the-art lane detection in an unordered crowdsourced image dataset. And we introduced TTLane, a dataset for efficient lane detection in urban road modeling applications. Combining LineNet and TTLane, we proposed a pipeline to model HD maps with crowdsourced data for the first time. And the maps can be constructed precisely even with inaccurate crowdsourced data. |
| Tasks | Lane Detection |
| Published | 2018-07-16 |
| URL | http://arxiv.org/abs/1807.05696v1 |
| http://arxiv.org/pdf/1807.05696v1.pdf | |
| PWC | https://paperswithcode.com/paper/linenet-a-zoomable-cnn-for-crowdsourced-high |
| Repo | |
| Framework | |
End-to-End Fingerprints Liveness Detection using Convolutional Networks with Gram module
| Title | End-to-End Fingerprints Liveness Detection using Convolutional Networks with Gram module |
| Authors | Eunsoo Park, Xuenan Cui, Weonjin Kim, Hakil Kim |
| Abstract | This paper proposes an end-to-end CNN(Convolutional Neural Networks) model that uses gram modules with parameters that are approximately 1.2MB in size to detect fake fingerprints. The proposed method assumes that texture is the most appropriate characteristic in fake fingerprint detection, and implements the gram module to extract textures from the CNN. The proposed CNN structure uses the fire module as the base model and uses the gram module for texture extraction. Tensors that passed the fire module will be joined with gram modules to create a gram matrix with the same spatial size. After 3 gram matrices extracted from different layers are combined with the channel axis, it becomes the basis for categorizing fake fingerprints. The experiment results had an average detection error of 2.61% from the LivDet 2011, 2013, 2015 data, proving that an end-to-end CNN structure with few parameters that is able to be used in fake fingerprint detection can be designed. |
| Tasks | |
| Published | 2018-03-21 |
| URL | http://arxiv.org/abs/1803.07830v1 |
| http://arxiv.org/pdf/1803.07830v1.pdf | |
| PWC | https://paperswithcode.com/paper/end-to-end-fingerprints-liveness-detection |
| Repo | |
| Framework | |
MASON: A Model AgnoStic ObjectNess Framework
| Title | MASON: A Model AgnoStic ObjectNess Framework |
| Authors | K J Joseph, Vineeth N Balasubramanian |
| Abstract | This paper proposes a simple, yet very effective method to localize dominant foreground objects in an image, to pixel-level precision. The proposed method ‘MASON’ (Model-AgnoStic ObjectNess) uses a deep convolutional network to generate category-independent and model-agnostic heat maps for any image. The network is not explicitly trained for the task, and hence, can be used off-the-shelf in tandem with any other network or task. We show that this framework scales to a wide variety of images, and illustrate the effectiveness of MASON in three varied application contexts. |
| Tasks | |
| Published | 2018-09-20 |
| URL | http://arxiv.org/abs/1809.07499v1 |
| http://arxiv.org/pdf/1809.07499v1.pdf | |
| PWC | https://paperswithcode.com/paper/mason-a-model-agnostic-objectness-framework |
| Repo | |
| Framework | |
On the Predictability of non-CGM Diabetes Data for Personalized Recommendation
| Title | On the Predictability of non-CGM Diabetes Data for Personalized Recommendation |
| Authors | Tu Ngoc Nguyen, Markus Rokicki |
| Abstract | With continuous glucose monitoring (CGM), data-driven models on blood glucose prediction have been shown to be effective in related work. However, such (CGM) systems are not always available, e.g., for a patient at home. In this work, we conduct a study on 9 patients and examine the predictability of data-driven (aka. machine learning) based models on patient-level blood glucose prediction; with measurements are taken only periodically (i.e., after several hours). To this end, we propose several post-prediction methods to account for the noise nature of these data, that marginally improves the performance of the end system. |
| Tasks | |
| Published | 2018-08-19 |
| URL | http://arxiv.org/abs/1808.07380v4 |
| http://arxiv.org/pdf/1808.07380v4.pdf | |
| PWC | https://paperswithcode.com/paper/on-the-predictability-of-non-cgm-diabetes |
| Repo | |
| Framework | |
Deep Reinforcement Learning for Dynamic Treatment Regimes on Medical Registry Data
| Title | Deep Reinforcement Learning for Dynamic Treatment Regimes on Medical Registry Data |
| Authors | Ning Liu, Ying Liu, Brent Logan, Zhiyuan Xu, Jian Tang, Yanzhi Wang |
| Abstract | This paper presents the first deep reinforcement learning (DRL) framework to estimate the optimal Dynamic Treatment Regimes from observational medical data. This framework is more flexible and adaptive for high dimensional action and state spaces than existing reinforcement learning methods to model real-life complexity in heterogeneous disease progression and treatment choices, with the goal of providing doctor and patients the data-driven personalized decision recommendations. The proposed DRL framework comprises (i) a supervised learning step to predict the most possible expert actions, and (ii) a deep reinforcement learning step to estimate the long-term value function of Dynamic Treatment Regimes. Both steps depend on deep neural networks. As a key motivational example, we have implemented the proposed framework on a data set from the Center for International Bone Marrow Transplant Research (CIBMTR) registry database, focusing on the sequence of prevention and treatments for acute and chronic graft versus host disease after transplantation. In the experimental results, we have demonstrated promising accuracy in predicting human experts’ decisions, as well as the high expected reward function in the DRL-based dynamic treatment regimes. |
| Tasks | |
| Published | 2018-01-28 |
| URL | http://arxiv.org/abs/1801.09271v1 |
| http://arxiv.org/pdf/1801.09271v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-reinforcement-learning-for-dynamic |
| Repo | |
| Framework | |
Multi-Scale Face Restoration with Sequential Gating Ensemble Network
| Title | Multi-Scale Face Restoration with Sequential Gating Ensemble Network |
| Authors | Jianxin Lin, Tiankuang Zhou, Zhibo Chen |
| Abstract | Restoring face images from distortions is important in face recognition applications and is challenged by multiple scale issues, which is still not well-solved in research area. In this paper, we present a Sequential Gating Ensemble Network (SGEN) for multi-scale face restoration issue. We first employ the principle of ensemble learning into SGEN architecture design to reinforce predictive performance of the network. The SGEN aggregates multi-level base-encoders and base-decoders into the network, which enables the network to contain multiple scales of receptive field. Instead of combining these base-en/decoders directly with non-sequential operations, the SGEN takes base-en/decoders from different levels as sequential data. Specifically, the SGEN learns to sequentially extract high level information from base-encoders in bottom-up manner and restore low level information from base-decoders in top-down manner. Besides, we propose to realize bottom-up and top-down information combination and selection with Sequential Gating Unit (SGU). The SGU sequentially takes two inputs from different levels and decides the output based on one active input. Experiment results demonstrate that our SGEN is more effective at multi-scale human face restoration with more image details and less noise than state-of-the-art image restoration models. By using adversarial training, SGEN also produces more visually preferred results than other models through subjective evaluation. |
| Tasks | Face Recognition, Image Restoration |
| Published | 2018-05-06 |
| URL | http://arxiv.org/abs/1805.02164v1 |
| http://arxiv.org/pdf/1805.02164v1.pdf | |
| PWC | https://paperswithcode.com/paper/multi-scale-face-restoration-with-sequential |
| Repo | |
| Framework | |
Distances for WiFi Based Topological Indoor Mapping
| Title | Distances for WiFi Based Topological Indoor Mapping |
| Authors | Bastian Schäfermeier, Tom Hanika, Gerd Stumme |
| Abstract | For localization and mapping of indoor environments through WiFi signals, locations are often represented as likelihoods of the received signal strength indicator. In this work we compare various measures of distance between such likelihoods in combination with different methods for estimation and representation. In particular, we show that among the considered distance measures the Earth Mover’s Distance seems the most beneficial for the localization task. Combined with kernel density estimation we were able to retain the topological structure of rooms in a real-world office scenario. |
| Tasks | Density Estimation |
| Published | 2018-09-19 |
| URL | http://arxiv.org/abs/1809.07405v1 |
| http://arxiv.org/pdf/1809.07405v1.pdf | |
| PWC | https://paperswithcode.com/paper/distances-for-wifi-based-topological-indoor |
| Repo | |
| Framework | |
Parallelization does not Accelerate Convex Optimization: Adaptivity Lower Bounds for Non-smooth Convex Minimization
| Title | Parallelization does not Accelerate Convex Optimization: Adaptivity Lower Bounds for Non-smooth Convex Minimization |
| Authors | Eric Balkanski, Yaron Singer |
| Abstract | In this paper we study the limitations of parallelization in convex optimization. A convenient approach to study parallelization is through the prism of \emph{adaptivity} which is an information theoretic measure of the parallel runtime of an algorithm [BS18]. Informally, adaptivity is the number of sequential rounds an algorithm needs to make when it can execute polynomially-many queries in parallel at every round. For combinatorial optimization with black-box oracle access, the study of adaptivity has recently led to exponential accelerations in parallel runtime and the natural question is whether dramatic accelerations are achievable for convex optimization. For the problem of minimizing a non-smooth convex function $f:[0,1]^n\to \mathbb{R}$ over the unit Euclidean ball, we give a tight lower bound that shows that even when $\texttt{poly}(n)$ queries can be executed in parallel, there is no randomized algorithm with $\tilde{o}(n^{1/3})$ rounds of adaptivity that has convergence rate that is better than those achievable with a one-query-per-round algorithm. A similar lower bound was obtained by Nemirovski [Nem94], however that result holds for the $\ell_{\infty}$-setting instead of $\ell_2$. In addition, we also show a tight lower bound that holds for Lipschitz and strongly convex functions. At the time of writing this manuscript we were not aware of Nemirovski’s result. The construction we use is similar to the one in [Nem94], though our analysis is different. Due to the close relationship between this work and [Nem94], we view the research contribution of this manuscript limited and it should serve as an instructful approach to understanding lower bounds for parallel optimization. |
| Tasks | Combinatorial Optimization |
| Published | 2018-08-12 |
| URL | https://arxiv.org/abs/1808.03880v2 |
| https://arxiv.org/pdf/1808.03880v2.pdf | |
| PWC | https://paperswithcode.com/paper/parallelization-does-not-accelerate-convex |
| Repo | |
| Framework | |
Learning Blind Video Temporal Consistency
| Title | Learning Blind Video Temporal Consistency |
| Authors | Wei-Sheng Lai, Jia-Bin Huang, Oliver Wang, Eli Shechtman, Ersin Yumer, Ming-Hsuan Yang |
| Abstract | Applying image processing algorithms independently to each frame of a video often leads to undesired inconsistent results over time. Developing temporally consistent video-based extensions, however, requires domain knowledge for individual tasks and is unable to generalize to other applications. In this paper, we present an efficient end-to-end approach based on deep recurrent network for enforcing temporal consistency in a video. Our method takes the original unprocessed and per-frame processed videos as inputs to produce a temporally consistent video. Consequently, our approach is agnostic to specific image processing algorithms applied on the original video. We train the proposed network by minimizing both short-term and long-term temporal losses as well as the perceptual loss to strike a balance between temporal stability and perceptual similarity with the processed frames. At test time, our model does not require computing optical flow and thus achieves real-time speed even for high-resolution videos. We show that our single model can handle multiple and unseen tasks, including but not limited to artistic style transfer, enhancement, colorization, image-to-image translation and intrinsic image decomposition. Extensive objective evaluation and subject study demonstrate that the proposed approach performs favorably against the state-of-the-art methods on various types of videos. |
| Tasks | Colorization, Image-to-Image Translation, Intrinsic Image Decomposition, Optical Flow Estimation, Style Transfer |
| Published | 2018-08-01 |
| URL | http://arxiv.org/abs/1808.00449v1 |
| http://arxiv.org/pdf/1808.00449v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-blind-video-temporal-consistency |
| Repo | |
| Framework | |
On Marginally Correct Approximations of Dempster-Shafer Belief Functions from Data
| Title | On Marginally Correct Approximations of Dempster-Shafer Belief Functions from Data |
| Authors | Mieczysław A. Kłopotek, Sławomir T. Wierzchoń |
| Abstract | Mathematical Theory of Evidence (MTE), a foundation for reasoning under partial ignorance, is blamed to leave frequencies outside (or aside of) its framework. The seriousness of this accusation is obvious: no experiment may be run to compare the performance of MTE-based models of real world processes against real world data. In this paper we consider this problem from the point of view of conditioning in the MTE. We describe the class of belief functions for which marginal consistency with observed frequencies may be achieved and conditional belief functions are proper belief functions,%\ and deal with implications for (marginal) approximation of general belief functions by this class of belief functions and for inference models in MTE. |
| Tasks | |
| Published | 2018-12-07 |
| URL | http://arxiv.org/abs/1812.02942v1 |
| http://arxiv.org/pdf/1812.02942v1.pdf | |
| PWC | https://paperswithcode.com/paper/on-marginally-correct-approximations-of |
| Repo | |
| Framework | |
