Paper Group ANR 1061
Inspiration Learning through Preferences. Full explicit consistency constraints in uncalibrated multiple homography estimation. Insights into the robustness of control point configurations for homography and planar pose estimation. Privacy-Preserving Deep Learning via Weight Transmission. Classifying medical relations in clinical text via convoluti …
Inspiration Learning through Preferences
Title | Inspiration Learning through Preferences |
Authors | Nir Baram, Shie Mannor |
Abstract | Current imitation learning techniques are too restrictive because they require the agent and expert to share the same action space. However, oftentimes agents that act differently from the expert can solve the task just as good. For example, a person lifting a box can be imitated by a ceiling mounted robot or a desktop-based robotic-arm. In both cases, the end goal of lifting the box is achieved, perhaps using different strategies. We denote this setup as \textit{Inspiration Learning} - knowledge transfer between agents that operate in different action spaces. Since state-action expert demonstrations can no longer be used, Inspiration learning requires novel methods to guide the agent towards the end goal. In this work, we rely on ideas of Preferential based Reinforcement Learning (PbRL) to design Advantage Actor-Critic algorithms for solving inspiration learning tasks. Unlike classic actor-critic architectures, the critic we use consists of two parts: a) a state-value estimation as in common actor-critic algorithms and b) a single step reward function derived from an expert/agent classifier. We show that our method is capable of extending the current imitation framework to new horizons. This includes continuous-to-discrete action imitation, as well as primitive-to-macro action imitation. |
Tasks | Imitation Learning, Transfer Learning |
Published | 2018-09-16 |
URL | http://arxiv.org/abs/1809.05872v1 |
http://arxiv.org/pdf/1809.05872v1.pdf | |
PWC | https://paperswithcode.com/paper/inspiration-learning-through-preferences |
Repo | |
Framework | |
Full explicit consistency constraints in uncalibrated multiple homography estimation
Title | Full explicit consistency constraints in uncalibrated multiple homography estimation |
Authors | Wojciech Chojnacki, Zygmunt L. Szpak |
Abstract | We reveal a complete set of constraints that need to be imposed on a set of 3-by-3 matrices to ensure that the matrices represent genuine homographies associated with multiple planes between two views. We also show how to exploit the constraints to obtain more accurate estimates of homography matrices between two views. Our study resolves a long-standing research question and provides a fresh perspective and a more in-depth understanding of the multiple homography estimation task. |
Tasks | Homography Estimation |
Published | 2018-05-07 |
URL | https://arxiv.org/abs/1805.02352v7 |
https://arxiv.org/pdf/1805.02352v7.pdf | |
PWC | https://paperswithcode.com/paper/full-explicit-consistency-constraints-in |
Repo | |
Framework | |
Insights into the robustness of control point configurations for homography and planar pose estimation
Title | Insights into the robustness of control point configurations for homography and planar pose estimation |
Authors | Raul Acuna, Volker Willert |
Abstract | In this paper, we investigate the influence of the spatial configuration of a number of $n \geq 4$ control points on the accuracy and robustness of space resection methods, e.g. used by a fiducial marker for pose estimation. We find robust configurations of control points by minimizing the first order perturbed solution of the DLT algorithm which is equivalent to minimizing the condition number of the data matrix. An empirical statistical evaluation is presented verifying that these optimized control point configurations not only increase the performance of the DLT homography estimation but also improve the performance of planar pose estimation methods like IPPE and EPnP, including the iterative minimization of the reprojection error which is the most accurate algorithm. We provide the characteristics of stable control point configurations for real-world noisy camera data that are practically independent on the camera pose and form certain symmetric patterns dependent on the number of points. Finally, we present a comparison of optimized configuration versus the number of control points. |
Tasks | Homography Estimation, Pose Estimation |
Published | 2018-03-08 |
URL | http://arxiv.org/abs/1803.03025v2 |
http://arxiv.org/pdf/1803.03025v2.pdf | |
PWC | https://paperswithcode.com/paper/insights-into-the-robustness-of-control-point |
Repo | |
Framework | |
Privacy-Preserving Deep Learning via Weight Transmission
Title | Privacy-Preserving Deep Learning via Weight Transmission |
Authors | Le Trieu Phong, Tran Thi Phuong |
Abstract | This paper considers the scenario that multiple data owners wish to apply a machine learning method over the combined dataset of all owners to obtain the best possible learning output but do not want to share the local datasets owing to privacy concerns. We design systems for the scenario that the stochastic gradient descent (SGD) algorithm is used as the machine learning method because SGD (or its variants) is at the heart of recent deep learning techniques over neural networks. Our systems differ from existing systems in the following features: {\bf (1)} any activation function can be used, meaning that no privacy-preserving-friendly approximation is required; {\bf (2)} gradients computed by SGD are not shared but the weight parameters are shared instead; and {\bf (3)} robustness against colluding parties even in the extreme case that only one honest party exists. We prove that our systems, while privacy-preserving, achieve the same learning accuracy as SGD and hence retain the merit of deep learning with respect to accuracy. Finally, we conduct several experiments using benchmark datasets, and show that our systems outperform previous system in terms of learning accuracies. |
Tasks | Privacy Preserving Deep Learning |
Published | 2018-09-10 |
URL | http://arxiv.org/abs/1809.03272v3 |
http://arxiv.org/pdf/1809.03272v3.pdf | |
PWC | https://paperswithcode.com/paper/privacy-preserving-deep-learning-via-weight |
Repo | |
Framework | |
Classifying medical relations in clinical text via convolutional neural networks
Title | Classifying medical relations in clinical text via convolutional neural networks |
Authors | Bin He, Yi Guan, Rui Dai |
Abstract | Deep learning research on relation classification has achieved solid performance in the general domain. This study proposes a convolutional neural network (CNN) architecture with a multi-pooling operation for medical relation classification on clinical records and explores a loss function with a category-level constraint matrix. Experiments using the 2010 i2b2/VA relation corpus demonstrate these models, which do not depend on any external features, outperform previous single-model methods and our best model is competitive with the existing ensemble-based method. |
Tasks | Relation Classification |
Published | 2018-05-17 |
URL | http://arxiv.org/abs/1805.06665v1 |
http://arxiv.org/pdf/1805.06665v1.pdf | |
PWC | https://paperswithcode.com/paper/classifying-medical-relations-in-clinical |
Repo | |
Framework | |
Finding Local Minima via Stochastic Nested Variance Reduction
Title | Finding Local Minima via Stochastic Nested Variance Reduction |
Authors | Dongruo Zhou, Pan Xu, Quanquan Gu |
Abstract | We propose two algorithms that can find local minima faster than the state-of-the-art algorithms in both finite-sum and general stochastic nonconvex optimization. At the core of the proposed algorithms is $\text{One-epoch-SNVRG}^+$ using stochastic nested variance reduction (Zhou et al., 2018a), which outperforms the state-of-the-art variance reduction algorithms such as SCSG (Lei et al., 2017). In particular, for finite-sum optimization problems, the proposed $\text{SNVRG}^{+}+\text{Neon2}^{\text{finite}}$ algorithm achieves $\tilde{O}(n^{1/2}\epsilon^{-2}+n\epsilon_H^{-3}+n^{3/4}\epsilon_H^{-7/2})$ gradient complexity to converge to an $(\epsilon, \epsilon_H)$-second-order stationary point, which outperforms $\text{SVRG}+\text{Neon2}^{\text{finite}}$ (Allen-Zhu and Li, 2017) , the best existing algorithm, in a wide regime. For general stochastic optimization problems, the proposed $\text{SNVRG}^{+}+\text{Neon2}^{\text{online}}$ achieves $\tilde{O}(\epsilon^{-3}+\epsilon_H^{-5}+\epsilon^{-2}\epsilon_H^{-3})$ gradient complexity, which is better than both $\text{SVRG}+\text{Neon2}^{\text{online}}$ (Allen-Zhu and Li, 2017) and Natasha2 (Allen-Zhu, 2017) in certain regimes. Furthermore, we explore the acceleration brought by third-order smoothness of the objective function. |
Tasks | Stochastic Optimization |
Published | 2018-06-22 |
URL | http://arxiv.org/abs/1806.08782v1 |
http://arxiv.org/pdf/1806.08782v1.pdf | |
PWC | https://paperswithcode.com/paper/finding-local-minima-via-stochastic-nested |
Repo | |
Framework | |
Reconstructing Gaussian sources by spatial sampling
Title | Reconstructing Gaussian sources by spatial sampling |
Authors | Vinay Praneeth Boda |
Abstract | Consider a Gaussian memoryless multiple source with $m$ components with joint probability distribution known only to lie in a given class of distributions. A subset of $k \leq m$ components are sampled and compressed with the objective of reconstructing all the $m$ components within a specified level of distortion under a mean-squared error criterion. In Bayesian and nonBayesian settings, the notion of universal sampling rate distortion function for Gaussian sources is introduced to capture the optimal tradeoffs among sampling, compression rate and distortion level. Single-letter characterizations are provided for the universal sampling rate distortion function. Our achievability proofs highlight the following structural property: it is optimal to compress and reconstruct first the sampled components of the GMMS alone, and then form estimates for the unsampled components based on the former. |
Tasks | |
Published | 2018-03-15 |
URL | http://arxiv.org/abs/1803.05605v1 |
http://arxiv.org/pdf/1803.05605v1.pdf | |
PWC | https://paperswithcode.com/paper/reconstructing-gaussian-sources-by-spatial |
Repo | |
Framework | |
Learning to Localize and Align Fine-Grained Actions to Sparse Instructions
Title | Learning to Localize and Align Fine-Grained Actions to Sparse Instructions |
Authors | Meera Hahn, Nataniel Ruiz, Jean-Baptiste Alayrac, Ivan Laptev, James M. Rehg |
Abstract | Automatic generation of textual video descriptions that are time-aligned with video content is a long-standing goal in computer vision. The task is challenging due to the difficulty of bridging the semantic gap between the visual and natural language domains. This paper addresses the task of automatically generating an alignment between a set of instructions and a first person video demonstrating an activity. The sparse descriptions and ambiguity of written instructions create significant alignment challenges. The key to our approach is the use of egocentric cues to generate a concise set of action proposals, which are then matched to recipe steps using object recognition and computational linguistic techniques. We obtain promising results on both the Extended GTEA Gaze+ dataset and the Bristol Egocentric Object Interactions Dataset. |
Tasks | Object Recognition |
Published | 2018-09-22 |
URL | http://arxiv.org/abs/1809.08381v1 |
http://arxiv.org/pdf/1809.08381v1.pdf | |
PWC | https://paperswithcode.com/paper/learning-to-localize-and-align-fine-grained |
Repo | |
Framework | |
Trifo-VIO: Robust and Efficient Stereo Visual Inertial Odometry using Points and Lines
Title | Trifo-VIO: Robust and Efficient Stereo Visual Inertial Odometry using Points and Lines |
Authors | Feng Zheng, Grace Tsai, Zhe Zhang, Shaoshan Liu, Chen-Chi Chu, Hongbing Hu |
Abstract | In this paper, we present the Trifo Visual Inertial Odometry (Trifo-VIO), a tightly-coupled filtering-based stereo VIO system using both points and lines. Line features help improve system robustness in challenging scenarios when point features cannot be reliably detected or tracked, e.g. low-texture environment or lighting change. In addition, we propose a novel lightweight filtering-based loop closing technique to reduce accumulated drift without global bundle adjustment or pose graph optimization. We formulate loop closure as EKF updates to optimally relocate the current sliding window maintained by the filter to past keyframes. We also present the Trifo Ironsides dataset, a new visual-inertial dataset, featuring high-quality synchronized stereo camera and IMU data from the Ironsides sensor [3] with various motion types and textures and millimeter-accuracy groundtruth. To validate the performance of the proposed system, we conduct extensive comparison with state-of-the-art approaches (OKVIS, VINS-MONO and S-MSCKF) using both the public EuRoC dataset and the Trifo Ironsides dataset. |
Tasks | |
Published | 2018-03-06 |
URL | http://arxiv.org/abs/1803.02403v2 |
http://arxiv.org/pdf/1803.02403v2.pdf | |
PWC | https://paperswithcode.com/paper/trifo-vio-robust-and-efficient-stereo-visual |
Repo | |
Framework | |
Autoencoder Based Residual Deep Networks for Robust Regression Prediction and Spatiotemporal Estimation
Title | Autoencoder Based Residual Deep Networks for Robust Regression Prediction and Spatiotemporal Estimation |
Authors | Lianfa Li, Ying Fang, Jun Wu, Jinfeng Wang |
Abstract | To have a superior generalization, a deep learning neural network often involves a large size of training sample. With increase of hidden layers in order to increase learning ability, neural network has potential degradation in accuracy. Both could seriously limit applicability of deep learning in some domains particularly involving predictions of continuous variables with a small size of samples. Inspired by residual convolutional neural network in computer vision and recent findings of crucial shortcuts in the brains in neuroscience, we propose an autoencoder-based residual deep network for robust prediction. In a nested way, we leverage shortcut connections to implement residual mapping with a balanced structure for efficient propagation of error signals. The novel method is demonstrated by multiple datasets, imputation of high spatiotemporal resolution non-randomness missing values of aerosol optical depth, and spatiotemporal estimation of fine particulate matter <2.5 \mu m, achieving the cutting edge of accuracy and efficiency. Our approach is also a general-purpose regression learner to be applicable in diverse domains. |
Tasks | Imputation |
Published | 2018-12-29 |
URL | http://arxiv.org/abs/1812.11262v1 |
http://arxiv.org/pdf/1812.11262v1.pdf | |
PWC | https://paperswithcode.com/paper/autoencoder-based-residual-deep-networks-for |
Repo | |
Framework | |
Survey of state-of-the-art mixed data clustering algorithms
Title | Survey of state-of-the-art mixed data clustering algorithms |
Authors | Amir Ahmad, Shehroz S. Khan |
Abstract | Mixed data comprises both numeric and categorical features, and mixed datasets occur frequently in many domains, such as health, finance, and marketing. Clustering is often applied to mixed datasets to find structures and to group similar objects for further analysis. However, clustering mixed data is challenging because it is difficult to directly apply mathematical operations, such as summation or averaging, to the feature values of these datasets. In this paper, we present a taxonomy for the study of mixed data clustering algorithms by identifying five major research themes. We then present a state-of-the-art review of the research works within each research theme. We analyze the strengths and weaknesses of these methods with pointers for future research directions. Lastly, we present an in-depth analysis of the overall challenges in this field, highlight open research questions and discuss guidelines to make progress in the field. |
Tasks | |
Published | 2018-11-11 |
URL | http://arxiv.org/abs/1811.04364v6 |
http://arxiv.org/pdf/1811.04364v6.pdf | |
PWC | https://paperswithcode.com/paper/a-survey-of-state-of-the-art-mixed-data |
Repo | |
Framework | |
G-SMOTE: A GMM-based synthetic minority oversampling technique for imbalanced learning
Title | G-SMOTE: A GMM-based synthetic minority oversampling technique for imbalanced learning |
Authors | Tianlun Zhang, Xi Yang |
Abstract | Imbalanced Learning is an important learning algorithm for the classification models, which have enjoyed much popularity on many applications. Typically, imbalanced learning algorithms can be partitioned into two types, i.e., data level approaches and algorithm level approaches. In this paper, the focus is to develop a robust synthetic minority oversampling technique which falls the umbrella of data level approaches. On one hand, we proposed a method to generate synthetic samples in a high dimensional feature space, instead of a linear sampling space. On the other hand, in the proposed imbalanced learning framework, Gaussian Mixture Model is employed to distinguish the outliers from minority class instances and filter out the synthetic majority class instances. Last and more importantly, an adaptive optimization method is proposed to optimize these parameters in sampling process. By doing so, an effectiveness and efficiency imbalanced learning framework is developed. |
Tasks | |
Published | 2018-10-24 |
URL | http://arxiv.org/abs/1810.10363v1 |
http://arxiv.org/pdf/1810.10363v1.pdf | |
PWC | https://paperswithcode.com/paper/g-smote-a-gmm-based-synthetic-minority |
Repo | |
Framework | |
Porosity Amount Estimation in Stones Based on Combination of One Dimensional Local Binary Patterns and Image Normalization Technique
Title | Porosity Amount Estimation in Stones Based on Combination of One Dimensional Local Binary Patterns and Image Normalization Technique |
Authors | Shervan Fekri-Ershad |
Abstract | Since now, many approaches has been proposed for surface defect detection based on image texture analysis techniques. One of the efficient texture analysis operations is local binary patterns which provides good accuracy. |
Tasks | Texture Classification |
Published | 2018-10-13 |
URL | http://arxiv.org/abs/1810.05922v1 |
http://arxiv.org/pdf/1810.05922v1.pdf | |
PWC | https://paperswithcode.com/paper/porosity-amount-estimation-in-stones-based-on |
Repo | |
Framework | |
Statistical shape analysis in a Bayesian framework for shapes in two and three dimensions
Title | Statistical shape analysis in a Bayesian framework for shapes in two and three dimensions |
Authors | Thomai Tsiftsi |
Abstract | In this paper, we describe a novel shape classification method which is embedded in the Bayesian paradigm. We discuss the modelling and the resulting shape classification algorithm for two and three dimensional data shapes. We conclude by evaluating the efficiency and efficacy of the proposed algorithm on the Kimia shape database for the two dimensional case. |
Tasks | |
Published | 2018-02-28 |
URL | http://arxiv.org/abs/1802.10570v1 |
http://arxiv.org/pdf/1802.10570v1.pdf | |
PWC | https://paperswithcode.com/paper/statistical-shape-analysis-in-a-bayesian |
Repo | |
Framework | |
Developing Far-Field Speaker System Via Teacher-Student Learning
Title | Developing Far-Field Speaker System Via Teacher-Student Learning |
Authors | Jinyu Li, Rui Zhao, Zhuo Chen, Changliang Liu, Xiong Xiao, Guoli Ye, Yifan Gong |
Abstract | In this study, we develop the keyword spotting (KWS) and acoustic model (AM) components in a far-field speaker system. Specifically, we use teacher-student (T/S) learning to adapt a close-talk well-trained production AM to far-field by using parallel close-talk and simulated far-field data. We also use T/S learning to compress a large-size KWS model into a small-size one to fit the device computational cost. Without the need of transcription, T/S learning well utilizes untranscribed data to boost the model performance in both the AM adaptation and KWS model compression. We further optimize the models with sequence discriminative training and live data to reach the best performance of systems. The adapted AM improved from the baseline by 72.60% and 57.16% relative word error rate reduction on play-back and live test data, respectively. The final KWS model size was reduced by 27 times from a large-size KWS model without losing accuracy. |
Tasks | Keyword Spotting, Model Compression |
Published | 2018-04-14 |
URL | http://arxiv.org/abs/1804.05166v1 |
http://arxiv.org/pdf/1804.05166v1.pdf | |
PWC | https://paperswithcode.com/paper/developing-far-field-speaker-system-via |
Repo | |
Framework | |