Paper Group ANR 1060
Morphology-Agnostic Visual Robotic Control. Investigating the effect of competitiveness power in estimating the average weighted price in electricity market. Deep splitting method for parabolic PDEs. Countering Noisy Labels By Learning From Auxiliary Clean Labels. Information Aggregation for Multi-Head Attention with Routing-by-Agreement. Deep mate …
Morphology-Agnostic Visual Robotic Control
| Title | Morphology-Agnostic Visual Robotic Control |
| Authors | Brian Yang, Dinesh Jayaraman, Glen Berseth, Alexei Efros, Sergey Levine |
| Abstract | Existing approaches for visuomotor robotic control typically require characterizing the robot in advance by calibrating the camera or performing system identification. We propose MAVRIC, an approach that works with minimal prior knowledge of the robot’s morphology, and requires only a camera view containing the robot and its environment and an unknown control interface. MAVRIC revolves around a mutual information-based method for self-recognition, which discovers visual “control points” on the robot body within a few seconds of exploratory interaction, and these control points in turn are then used for visual servoing. MAVRIC can control robots with imprecise actuation, no proprioceptive feedback, unknown morphologies including novel tools, unknown camera poses, and even unsteady handheld cameras. We demonstrate our method on visually-guided 3D point reaching, trajectory following, and robot-to-robot imitation. |
| Tasks | |
| Published | 2019-12-31 |
| URL | https://arxiv.org/abs/1912.13360v1 |
| https://arxiv.org/pdf/1912.13360v1.pdf | |
| PWC | https://paperswithcode.com/paper/morphology-agnostic-visual-robotic-control |
| Repo | |
| Framework | |
Investigating the effect of competitiveness power in estimating the average weighted price in electricity market
| Title | Investigating the effect of competitiveness power in estimating the average weighted price in electricity market |
| Authors | Naser Rostamni, Tarik A. Rashid |
| Abstract | This paper evaluates the impact of the power extent on price in the electricity market. The competitiveness extent of the electricity market during specific times in a day is considered to achieve this. Then, the effect of competitiveness extent on the forecasting precision of the daily power price is assessed. A price forecasting model based on multi-layer perception via back propagation with the Levenberg-Marquardt mechanism is used. The Residual Supply Index (RSI) and other variables that affect prices are used as inputs to the model to evaluate the market competitiveness. The results show that using market power indices as inputs helps to increase forecasting accuracy. Thus, the competitiveness extent of the market power in different daily time periods is a notable variable in price formation. Moreover, market players cannot ignore the explanatory power of market power in price forecasting. In this research, the real data of the electricity market from 2013 is used and the main source of data is the Grid Management Company in Iran. |
| Tasks | |
| Published | 2019-07-27 |
| URL | https://arxiv.org/abs/1907.11984v1 |
| https://arxiv.org/pdf/1907.11984v1.pdf | |
| PWC | https://paperswithcode.com/paper/investigating-the-effect-of-competitiveness |
| Repo | |
| Framework | |
Deep splitting method for parabolic PDEs
| Title | Deep splitting method for parabolic PDEs |
| Authors | Christian Beck, Sebastian Becker, Patrick Cheridito, Arnulf Jentzen, Ariel Neufeld |
| Abstract | In this paper we introduce a numerical method for parabolic PDEs that combines operator splitting with deep learning. It divides the PDE approximation problem into a sequence of separate learning problems. Since the computational graph for each of the subproblems is comparatively small, the approach can handle extremely high-dimensional PDEs. We test the method on different examples from physics, stochastic control, and mathematical finance. In all cases, it yields very good results in up to 10,000 dimensions with short run times. |
| Tasks | |
| Published | 2019-07-08 |
| URL | https://arxiv.org/abs/1907.03452v1 |
| https://arxiv.org/pdf/1907.03452v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-splitting-method-for-parabolic-pdes |
| Repo | |
| Framework | |
Countering Noisy Labels By Learning From Auxiliary Clean Labels
| Title | Countering Noisy Labels By Learning From Auxiliary Clean Labels |
| Authors | Tsung Wei Tsai, Chongxuan Li, Jun Zhu |
| Abstract | We consider the learning from noisy labels (NL) problem which emerges in many real-world applications. In addition to the widely-studied synthetic noise in the NL literature, we also consider the pseudo labels in semi-supervised learning (Semi-SL) as a special case of NL. For both types of noise, we argue that the generalization performance of existing methods is highly coupled with the quality of noisy labels. Therefore, we counter the problem from a novel and unified perspective: learning from the auxiliary clean labels. Specifically, we propose the Rotational-Decoupling Consistency Regularization (RDCR) framework that integrates the consistency-based methods with the self-supervised rotation task to learn noise-tolerant representations. The experiments show that RDCR achieves comparable or superior performance than the state-of-the-art methods under small noise, while outperforms the existing methods significantly when there is large noise. |
| Tasks | |
| Published | 2019-05-23 |
| URL | https://arxiv.org/abs/1905.13305v2 |
| https://arxiv.org/pdf/1905.13305v2.pdf | |
| PWC | https://paperswithcode.com/paper/190513305 |
| Repo | |
| Framework | |
Information Aggregation for Multi-Head Attention with Routing-by-Agreement
| Title | Information Aggregation for Multi-Head Attention with Routing-by-Agreement |
| Authors | Jian Li, Baosong Yang, Zi-Yi Dou, Xing Wang, Michael R. Lyu, Zhaopeng Tu |
| Abstract | Multi-head attention is appealing for its ability to jointly extract different types of information from multiple representation subspaces. Concerning the information aggregation, a common practice is to use a concatenation followed by a linear transformation, which may not fully exploit the expressiveness of multi-head attention. In this work, we propose to improve the information aggregation for multi-head attention with a more powerful routing-by-agreement algorithm. Specifically, the routing algorithm iteratively updates the proportion of how much a part (i.e. the distinct information learned from a specific subspace) should be assigned to a whole (i.e. the final output representation), based on the agreement between parts and wholes. Experimental results on linguistic probing tasks and machine translation tasks prove the superiority of the advanced information aggregation over the standard linear transformation. |
| Tasks | Machine Translation |
| Published | 2019-04-05 |
| URL | http://arxiv.org/abs/1904.03100v1 |
| http://arxiv.org/pdf/1904.03100v1.pdf | |
| PWC | https://paperswithcode.com/paper/information-aggregation-for-multi-head |
| Repo | |
| Framework | |
Deep material network with cohesive layers: Multi-stage training and interfacial failure analysis
| Title | Deep material network with cohesive layers: Multi-stage training and interfacial failure analysis |
| Authors | Zeliang Liu |
| Abstract | A fundamental issue in multiscale materials modeling and design is the consideration of traction-separation behavior at the interface. By enriching the deep material network (DMN) with cohesive layers, the paper presents a novel data-driven material model which enables accurate and efficient prediction of multiscale responses for heterogeneous materials with interfacial effect. In the newly invoked cohesive building block, the fitting parameters have physical meanings related to the length scale and orientation of the cohesive layer. It is shown that the enriched material network can be effectively optimized via a multi-stage training strategy, with training data generated only from linear elastic direct numerical simulation (DNS). The extrapolation capability of the method to unknown material and loading spaces is demonstrated through the debonding analysis of a unidirectional fiber-reinforced composite, where the interface behavior is governed by an irreversible softening mixed-mode cohesive law. Its predictive accuracy is validated against the nonlinear path-dependent DNS results, and the reduction in computational time is particularly significant. |
| Tasks | |
| Published | 2019-08-07 |
| URL | https://arxiv.org/abs/1908.04858v2 |
| https://arxiv.org/pdf/1908.04858v2.pdf | |
| PWC | https://paperswithcode.com/paper/deep-material-network-with-cohesive-layers |
| Repo | |
| Framework | |
Lifting AutoEncoders: Unsupervised Learning of a Fully-Disentangled 3D Morphable Model using Deep Non-Rigid Structure from Motion
| Title | Lifting AutoEncoders: Unsupervised Learning of a Fully-Disentangled 3D Morphable Model using Deep Non-Rigid Structure from Motion |
| Authors | Mihir Sahasrabudhe, Zhixin Shu, Edward Bartrum, Riza Alp Guler, Dimitris Samaras, Iasonas Kokkinos |
| Abstract | In this work we introduce Lifting Autoencoders, a generative 3D surface-based model of object categories. We bring together ideas from non-rigid structure from motion, image formation, and morphable models to learn a controllable, geometric model of 3D categories in an entirely unsupervised manner from an unstructured set of images. We exploit the 3D geometric nature of our model and use normal information to disentangle appearance into illumination, shading and albedo. We further use weak supervision to disentangle the non-rigid shape variability of human faces into identity and expression. We combine the 3D representation with a differentiable renderer to generate RGB images and append an adversarially trained refinement network to obtain sharp, photorealistic image reconstruction results. The learned generative model can be controlled in terms of interpretable geometry and appearance factors, allowing us to perform photorealistic image manipulation of identity, expression, 3D pose, and illumination properties. |
| Tasks | Image Reconstruction |
| Published | 2019-04-26 |
| URL | http://arxiv.org/abs/1904.11960v1 |
| http://arxiv.org/pdf/1904.11960v1.pdf | |
| PWC | https://paperswithcode.com/paper/lifting-autoencoders-unsupervised-learning-of |
| Repo | |
| Framework | |
3D pavement surface reconstruction using an RGB-D sensor
| Title | 3D pavement surface reconstruction using an RGB-D sensor |
| Authors | Ahmadreza Mahmoudzadeh, Sayna Firoozi Yeganeh, Amir Golroo |
| Abstract | A core procedure of pavement management systems is data collection. The modern technologies which are used for this purpose, such as point-based lasers and laser scanners, are too expensive to purchase, operate, and maintain. Thus, it is rarely feasible for city officials in developing countries to conduct data collection using these devices. This paper aims to introduce a cost-effective technology which can be used for pavement distress data collection and 3D pavement surface reconstruction. The applied technology in this research is the Kinect sensor which is not only cost-effective but also sufficiently precise. The Kinect sensor can register both depth and color images simultaneously. A cart is designed to mount an array of Kinect sensors. The cameras are calibrated and the slopes of collected surfaces are corrected via the Singular Value Decomposition (SVD) algorithm. Then, a procedure is proposed for stitching the RGB-D (Red Green Blue Depth) images using SURF (Speeded-up Robust Features) and MSAC (M-estimator SAmple Consensus) algorithms in order to create a 3D-structure of the pavement surface. Finally, transverse profiles are extracted and some field experiments are conducted to evaluate the reliability of the proposed approach for detecting pavement surface defects. |
| Tasks | |
| Published | 2019-07-09 |
| URL | https://arxiv.org/abs/1907.04124v2 |
| https://arxiv.org/pdf/1907.04124v2.pdf | |
| PWC | https://paperswithcode.com/paper/3d-pavement-surface-reconstruction-using-an |
| Repo | |
| Framework | |
Continuous Outlier Mining of Streaming Data in Flink
| Title | Continuous Outlier Mining of Streaming Data in Flink |
| Authors | Theodoros Toliopoulos, Anastasios Gounaris, Kostas Tsichlas, Apostolos Papadopoulos, Sandra Sampaio |
| Abstract | In this work, we focus on distance-based outliers in a metric space, where the status of an entity as to whether it is an outlier is based on the number of other entities in its neighborhood. In recent years, several solutions have tackled the problem of distance-based outliers in data streams, where outliers must be mined continuously as new elements become available. An interesting research problem is to combine the streaming environment with massively parallel systems to provide scalable streambased algorithms. However, none of the previously proposed techniques refer to a massively parallel setting. Our proposal fills this gap and investigates the challenges in transferring state-of-the-art techniques to Apache Flink, a modern platform for intensive streaming analytics. We thoroughly present the technical challenges encountered and the alternatives that may be applied. We show speed-ups of up to 117 (resp. 2076) times over a naive parallel (resp. non-parallel) solution in Flink, by using just an ordinary four-core machine and a real-world dataset. When moving to a three-machine cluster, due to less contention, we manage to achieve both better scalability in terms of the window slide size and the data dimensionality, and even higher speed-ups, e.g., by a factor of 510. Overall, our results demonstrate that oulier mining can be achieved in an efficient and scalable manner. The resulting techniques have been made publicly available as open-source software. |
| Tasks | |
| Published | 2019-02-21 |
| URL | http://arxiv.org/abs/1902.07901v1 |
| http://arxiv.org/pdf/1902.07901v1.pdf | |
| PWC | https://paperswithcode.com/paper/continuous-outlier-mining-of-streaming-data |
| Repo | |
| Framework | |
Deep Reinforcement Learning Architecture for Continuous Power Allocation in High Throughput Satellites
| Title | Deep Reinforcement Learning Architecture for Continuous Power Allocation in High Throughput Satellites |
| Authors | Juan Jose Garau Luis, Markus Guerster, Inigo del Portillo, Edward Crawley, Bruce Cameron |
| Abstract | In the coming years, the satellite broadband market will experience significant increases in the service demand, especially for the mobility sector, where demand is burstier. Many of the next generation of satellites will be equipped with numerous degrees of freedom in power and bandwidth allocation capabilities, making manual resource allocation impractical and inefficient. Therefore, it is desirable to automate the operation of these highly flexible satellites. This paper presents a novel power allocation approach based on Deep Reinforcement Learning (DRL) that represents the problem as continuous state and action spaces. We make use of the Proximal Policy Optimization (PPO) algorithm to optimize the allocation policy for minimum Unmet System Demand (USD) and power consumption. The performance of the algorithm is analyzed through simulations of a multibeam satellite system, which show promising results for DRL to be used as a dynamic resource allocation algorithm. |
| Tasks | |
| Published | 2019-06-03 |
| URL | https://arxiv.org/abs/1906.00571v1 |
| https://arxiv.org/pdf/1906.00571v1.pdf | |
| PWC | https://paperswithcode.com/paper/190600571 |
| Repo | |
| Framework | |
Meta Label Correction for Learning with Weak Supervision
| Title | Meta Label Correction for Learning with Weak Supervision |
| Authors | Guoqing Zheng, Ahmed Hassan Awadallah, Susan Dumais |
| Abstract | Leveraging weak or noisy supervision for building effective machine learning models has long been an important research problem. The growing need for large-scale datasets to train deep learning models has increased its importance. Weak or noisy supervision could originate from multiple sources including non-expert annotators or automatic labeling based on heuristics or user interaction signals. Previous work on modeling and correcting weak labels have been focused on various aspects, including loss correction, training instance re-weighting, etc. In this paper, we approach this problem from a novel perspective based on meta-learning. We view the label correction procedure as a meta-process and propose a new meta-learning based framework termed MLC for learning with weak supervision. Experiments with different label noise levels on multiple datasets show that MLC can achieve large improvement over previous methods incorporating weak labels for learning. |
| Tasks | Meta-Learning |
| Published | 2019-11-10 |
| URL | https://arxiv.org/abs/1911.03809v1 |
| https://arxiv.org/pdf/1911.03809v1.pdf | |
| PWC | https://paperswithcode.com/paper/meta-label-correction-for-learning-with-weak-1 |
| Repo | |
| Framework | |
Variable-sized input, character-level recurrent neural networks in lead generation: predicting close rates from raw user inputs
| Title | Variable-sized input, character-level recurrent neural networks in lead generation: predicting close rates from raw user inputs |
| Authors | Giulio Giorcelli |
| Abstract | Predicting lead close rates is one of the most problematic tasks in the lead generation industry. In most cases, the only available data on the prospect is the self-reported information inputted by the user on the lead form and a few other data points publicly available through social media and search engine usage. All the major market niches for lead generation [1], such as insurance, health & medical and real estate, deal with life-altering decision making that no amount of data will be ever be able to describe or predict. This paper illustrates how character-level, deep long short-term memory networks can be applied to raw user inputs to help predict close rates. The output of the model is then used as an additional, highly predictive feature to significantly boost performance of lead scoring models. |
| Tasks | Decision Making |
| Published | 2019-01-16 |
| URL | http://arxiv.org/abs/1901.05115v1 |
| http://arxiv.org/pdf/1901.05115v1.pdf | |
| PWC | https://paperswithcode.com/paper/variable-sized-input-character-level |
| Repo | |
| Framework | |
MAIN: Multi-Attention Instance Network for Video Segmentation
| Title | MAIN: Multi-Attention Instance Network for Video Segmentation |
| Authors | Juan Leon Alcazar, Maria A. Bravo, Ali K. Thabet, Guillaume Jeanneret, Thomas Brox, Pablo Arbelaez, Bernard Ghanem |
| Abstract | Instance-level video segmentation requires a solid integration of spatial and temporal information. However, current methods rely mostly on domain-specific information (online learning) to produce accurate instance-level segmentations. We propose a novel approach that relies exclusively on the integration of generic spatio-temporal attention cues. Our strategy, named Multi-Attention Instance Network (MAIN), overcomes challenging segmentation scenarios over arbitrary videos without modelling sequence- or instance-specific knowledge. We design MAIN to segment multiple instances in a single forward pass, and optimize it with a novel loss function that favors class agnostic predictions and assigns instance-specific penalties. We achieve state-of-the-art performance on the challenging Youtube-VOS dataset and benchmark, improving the unseen Jaccard and F-Metric by 6.8% and 12.7% respectively, while operating at real-time (30.3 FPS). |
| Tasks | Video Semantic Segmentation |
| Published | 2019-04-11 |
| URL | http://arxiv.org/abs/1904.05847v1 |
| http://arxiv.org/pdf/1904.05847v1.pdf | |
| PWC | https://paperswithcode.com/paper/main-multi-attention-instance-network-for |
| Repo | |
| Framework | |
The Bregman-Tweedie Classification Model
| Title | The Bregman-Tweedie Classification Model |
| Authors | Hyenkyun Woo |
| Abstract | This work proposes the Bregman-Tweedie classification model and analyzes the domain structure of the extended exponential function, an extension of the classic generalized exponential function with additional scaling parameter, and related high-level mathematical structures, such as the Bregman-Tweedie loss function and the Bregman-Tweedie divergence. The base function of this divergence is the convex function of Legendre type induced from the extended exponential function. The Bregman-Tweedie loss function of the proposed classification model is the regular Legendre transformation of the Bregman-Tweedie divergence. This loss function is a polynomial parameterized function between unhinge loss and the logistic loss function. Actually, we have two sub-models of the Bregman-Tweedie classification model; H-Bregman with hinge-like loss function and L-Bregman with logistic-like loss function. Although the proposed classification model is nonconvex and unbounded, empirically, we have observed that the H-Bregman and L-Bregman outperform, in terms of the Friedman ranking, logistic regression and SVM and show reasonable performance in terms of the classification accuracy in the category of the binary linear classification problem. |
| Tasks | |
| Published | 2019-07-16 |
| URL | https://arxiv.org/abs/1907.06923v1 |
| https://arxiv.org/pdf/1907.06923v1.pdf | |
| PWC | https://paperswithcode.com/paper/the-bregman-tweedie-classification-model |
| Repo | |
| Framework | |
Robust Alignment for Panoramic Stitching via an Exact Rank Constraint
| Title | Robust Alignment for Panoramic Stitching via an Exact Rank Constraint |
| Authors | Yuelong Li, Mohammad Tofighi, Vishal Monga |
| Abstract | We study the problem of image alignment for panoramic stitching. Unlike most existing approaches that are feature-based, our algorithm works on pixels directly, and accounts for errors across the whole images globally. Technically, we formulate the alignment problem as rank-1 and sparse matrix decomposition over transformed images, and develop an efficient algorithm for solving this challenging non-convex optimization problem. The algorithm reduces to solving a sequence of subproblems, where we analytically establish exact recovery conditions, convergence and optimality, together with convergence rate and complexity. We generalize it to simultaneously align multiple images and recover multiple homographies, extending its application scope towards vast majority of practical scenarios. Experimental results demonstrate that the proposed algorithm is capable of more accurately aligning the images and generating higher quality stitched images than state-of-the-art methods. |
| Tasks | |
| Published | 2019-04-01 |
| URL | http://arxiv.org/abs/1904.04158v1 |
| http://arxiv.org/pdf/1904.04158v1.pdf | |
| PWC | https://paperswithcode.com/paper/robust-alignment-for-panoramic-stitching-via |
| Repo | |
| Framework | |
