Paper Group ANR 107
Unsupervised Domain Adaptation for Learning Eye Gaze from a Million Synthetic Images: An Adversarial Approach. Kalman-based Spectro-Temporal ECG Analysis using Deep Convolutional Networks for Atrial Fibrillation Detection. A Feature Clustering Approach Based on Histogram of Oriented Optical Flow and Superpixels. Non-Intrusive Signature Extraction f …
Unsupervised Domain Adaptation for Learning Eye Gaze from a Million Synthetic Images: An Adversarial Approach
| Title | Unsupervised Domain Adaptation for Learning Eye Gaze from a Million Synthetic Images: An Adversarial Approach |
| Authors | Avisek Lahiri, Abhinav Agarwalla, Prabir Kumar Biswas |
| Abstract | With contemporary advancements of graphics engines, recent trend in deep learning community is to train models on automatically annotated simulated examples and apply on real data during test time. This alleviates the burden of manual annotation. However, there is an inherent difference of distributions between images coming from graphics engine and real world. Such domain difference deteriorates test time performances of models trained on synthetic examples. In this paper we address this issue with unsupervised adversarial feature adaptation across synthetic and real domain for the special use case of eye gaze estimation which is an essential component for various downstream HCI tasks. We initially learn a gaze estimator on annotated synthetic samples rendered from a 3D game engine and then adapt the features of unannotated real samples via a zero-sum minmax adversarial game against a domain discriminator following the recent paradigm of generative adversarial networks. Such adversarial adaptation forces features of both domains to be indistinguishable which enables us to use regression models trained on synthetic domain to be used on real samples. On the challenging MPIIGaze real life dataset, we outperform recent fully supervised methods trained on manually annotated real samples by appreciable margins and also achieve 13% more relative gain after adaptation compared to the current benchmark method of SimGAN |
| Tasks | Domain Adaptation, Gaze Estimation, Unsupervised Domain Adaptation |
| Published | 2018-10-18 |
| URL | http://arxiv.org/abs/1810.07926v1 |
| http://arxiv.org/pdf/1810.07926v1.pdf | |
| PWC | https://paperswithcode.com/paper/unsupervised-domain-adaptation-for-learning |
| Repo | |
| Framework | |
Kalman-based Spectro-Temporal ECG Analysis using Deep Convolutional Networks for Atrial Fibrillation Detection
| Title | Kalman-based Spectro-Temporal ECG Analysis using Deep Convolutional Networks for Atrial Fibrillation Detection |
| Authors | Zheng Zhao, Simo Särkkä, Ali Bahrami Rad |
| Abstract | In this article, we propose a novel ECG classification framework for atrial fibrillation (AF) detection using spectro-temporal representation (i.e., time varying spectrum) and deep convolutional networks. In the first step we use a Bayesian spectro-temporal representation based on the estimation of time-varying coefficients of Fourier series using Kalman filter and smoother. Next, we derive an alternative model based on a stochastic oscillator differential equation to accelerate the estimation of the spectro-temporal representation in lengthy signals. Finally, after comparative evaluations of different convolutional architectures, we propose an efficient deep convolutional neural network to classify the 2D spectro-temporal ECG data. The ECG spectro-temporal data are classified into four different classes: AF, non-AF normal rhythm (Normal), non-AF abnormal rhythm (Other), and noisy segments (Noisy). The performance of the proposed methods is evaluated and scored with the PhysioNet/Computing in Cardiology (CinC) 2017 dataset. The experimental results show that the proposed method achieves the overall F1 score of 80.2%, which is in line with the state-of-the-art algorithms. |
| Tasks | Atrial Fibrillation Detection, ECG Classification |
| Published | 2018-12-12 |
| URL | http://arxiv.org/abs/1812.05555v1 |
| http://arxiv.org/pdf/1812.05555v1.pdf | |
| PWC | https://paperswithcode.com/paper/kalman-based-spectro-temporal-ecg-analysis |
| Repo | |
| Framework | |
A Feature Clustering Approach Based on Histogram of Oriented Optical Flow and Superpixels
| Title | A Feature Clustering Approach Based on Histogram of Oriented Optical Flow and Superpixels |
| Authors | A. M. R. R. Bandara, L. Ranathunga, N. A. Abdullah |
| Abstract | Visual feature clustering is one of the cost-effective approaches to segment objects in videos. However, the assumptions made for developing the existing algorithms prevent them from being used in situations like segmenting an unknown number of static and moving objects under heavy camera movements. This paper addresses the problem by introducing a clustering approach based on superpixels and short-term Histogram of Oriented Optical Flow (HOOF). Salient Dither Pattern Feature (SDPF) is used as the visual feature to track the flow and Simple Linear Iterative Clustering (SLIC) is used for obtaining the superpixels. This new clustering approach is based on merging superpixels by comparing short term local HOOF and a color cue to form high-level semantic segments. The new approach was compared with one of the latest feature clustering approaches based on K-Means in eight-dimensional space and the results revealed that the new approach is better by means of consistency, completeness, and spatial accuracy. Further, the new approach completely solved the problem of not knowing the number of objects in a scene. |
| Tasks | Optical Flow Estimation |
| Published | 2018-02-28 |
| URL | http://arxiv.org/abs/1803.00031v1 |
| http://arxiv.org/pdf/1803.00031v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-feature-clustering-approach-based-on |
| Repo | |
| Framework | |
Non-Intrusive Signature Extraction for Major Residential Loads
| Title | Non-Intrusive Signature Extraction for Major Residential Loads |
| Authors | M. Dong, P. C. M. Meira, W. Xu, C. Y. Chung |
| Abstract | The data collected by smart meters contain a lot of useful information. One potential use of the data is to track the energy consumptions and operating statuses of major home appliances.The results will enable homeowners to make sound decisions on how to save energy and how to participate in demand response programs. This paper presents a new method to breakdown the total power demand measured by a smart meter to those used by individual appliances. A unique feature of the proposed method is that it utilizes diverse signatures associated with the entire operating window of an appliance for identification. As a result, appliances with complicated middle process can be tracked. A novel appliance registration device and scheme is also proposed to automate the creation of appliance signature database and to eliminate the need of massive training before identification. The software and system have been developed and deployed to real houses in order to verify the proposed method. |
| Tasks | |
| Published | 2018-04-30 |
| URL | http://arxiv.org/abs/1804.11049v1 |
| http://arxiv.org/pdf/1804.11049v1.pdf | |
| PWC | https://paperswithcode.com/paper/non-intrusive-signature-extraction-for-major |
| Repo | |
| Framework | |
Improving the Interpretability of Deep Neural Networks with Knowledge Distillation
| Title | Improving the Interpretability of Deep Neural Networks with Knowledge Distillation |
| Authors | Xuan Liu, Xiaoguang Wang, Stan Matwin |
| Abstract | Deep Neural Networks have achieved huge success at a wide spectrum of applications from language modeling, computer vision to speech recognition. However, nowadays, good performance alone is not sufficient to satisfy the needs of practical deployment where interpretability is demanded for cases involving ethics and mission critical applications. The complex models of Deep Neural Networks make it hard to understand and reason the predictions, which hinders its further progress. To tackle this problem, we apply the Knowledge Distillation technique to distill Deep Neural Networks into decision trees in order to attain good performance and interpretability simultaneously. We formulate the problem at hand as a multi-output regression problem and the experiments demonstrate that the student model achieves significantly better accuracy performance (about 1% to 5%) than vanilla decision trees at the same level of tree depth. The experiments are implemented on the TensorFlow platform to make it scalable to big datasets. To the best of our knowledge, we are the first to distill Deep Neural Networks into vanilla decision trees on multi-class datasets. |
| Tasks | Language Modelling, Speech Recognition |
| Published | 2018-12-28 |
| URL | http://arxiv.org/abs/1812.10924v1 |
| http://arxiv.org/pdf/1812.10924v1.pdf | |
| PWC | https://paperswithcode.com/paper/improving-the-interpretability-of-deep-neural |
| Repo | |
| Framework | |
Vector Field Based Neural Networks
| Title | Vector Field Based Neural Networks |
| Authors | Daniel Vieira, Fabio Rangel, Fabricio Firmino, Joao Paixao |
| Abstract | A novel Neural Network architecture is proposed using the mathematically and physically rich idea of vector fields as hidden layers to perform nonlinear transformations in the data. The data points are interpreted as particles moving along a flow defined by the vector field which intuitively represents the desired movement to enable classification. The architecture moves the data points from their original configuration to anew one following the streamlines of the vector field with the objective of achieving a final configuration where classes are separable. An optimization problem is solved through gradient descent to learn this vector field. |
| Tasks | |
| Published | 2018-02-22 |
| URL | http://arxiv.org/abs/1802.08235v1 |
| http://arxiv.org/pdf/1802.08235v1.pdf | |
| PWC | https://paperswithcode.com/paper/vector-field-based-neural-networks |
| Repo | |
| Framework | |
Creating Fair Models of Atherosclerotic Cardiovascular Disease Risk
| Title | Creating Fair Models of Atherosclerotic Cardiovascular Disease Risk |
| Authors | Stephen Pfohl, Ben Marafino, Adrien Coulet, Fatima Rodriguez, Latha Palaniappan, Nigam H. Shah |
| Abstract | Guidelines for the management of atherosclerotic cardiovascular disease (ASCVD) recommend the use of risk stratification models to identify patients most likely to benefit from cholesterol-lowering and other therapies. These models have differential performance across race and gender groups with inconsistent behavior across studies, potentially resulting in an inequitable distribution of beneficial therapy. In this work, we leverage adversarial learning and a large observational cohort extracted from electronic health records (EHRs) to develop a “fair” ASCVD risk prediction model with reduced variability in error rates across groups. We empirically demonstrate that our approach is capable of aligning the distribution of risk predictions conditioned on the outcome across several groups simultaneously for models built from high-dimensional EHR data. We also discuss the relevance of these results in the context of the empirical trade-off between fairness and model performance. |
| Tasks | |
| Published | 2018-09-12 |
| URL | https://arxiv.org/abs/1809.04663v3 |
| https://arxiv.org/pdf/1809.04663v3.pdf | |
| PWC | https://paperswithcode.com/paper/creating-fair-models-of-atherosclerotic |
| Repo | |
| Framework | |
ISA$^2$: Intelligent Speed Adaptation from Appearance
| Title | ISA$^2$: Intelligent Speed Adaptation from Appearance |
| Authors | Carlos Herranz-Perdiguero, Roberto J. López-Sastre |
| Abstract | In this work we introduce a new problem named Intelligent Speed Adaptation from Appearance (ISA$^2$). Technically, the goal of an ISA$^2$ model is to predict for a given image of a driving scenario the proper speed of the vehicle. Note this problem is different from predicting the actual speed of the vehicle. It defines a novel regression problem where the appearance information has to be directly mapped to get a prediction for the speed at which the vehicle should go, taking into account the traffic situation. First, we release a novel dataset for the new problem, where multiple driving video sequences, with the annotated adequate speed per frame, are provided. We then introduce two deep learning based ISA$^2$ models, which are trained to perform the final regression of the proper speed given a test image. We end with a thorough experimental validation where the results show the level of difficulty of the proposed task. The dataset and the proposed models will all be made publicly available to encourage much needed further research on this problem. |
| Tasks | |
| Published | 2018-10-11 |
| URL | http://arxiv.org/abs/1810.05016v1 |
| http://arxiv.org/pdf/1810.05016v1.pdf | |
| PWC | https://paperswithcode.com/paper/isa2-intelligent-speed-adaptation-from |
| Repo | |
| Framework | |
Vision-Aided Absolute Trajectory Estimation Using an Unsupervised Deep Network with Online Error Correction
| Title | Vision-Aided Absolute Trajectory Estimation Using an Unsupervised Deep Network with Online Error Correction |
| Authors | E. Jared Shamwell, Sarah Leung, William D. Nothwang |
| Abstract | We present an unsupervised deep neural network approach to the fusion of RGB-D imagery with inertial measurements for absolute trajectory estimation. Our network, dubbed the Visual-Inertial-Odometry Learner (VIOLearner), learns to perform visual-inertial odometry (VIO) without inertial measurement unit (IMU) intrinsic parameters (corresponding to gyroscope and accelerometer bias or white noise) or the extrinsic calibration between an IMU and camera. The network learns to integrate IMU measurements and generate hypothesis trajectories which are then corrected online according to the Jacobians of scaled image projection errors with respect to a spatial grid of pixel coordinates. We evaluate our network against state-of-the-art (SOA) visual-inertial odometry, visual odometry, and visual simultaneous localization and mapping (VSLAM) approaches on the KITTI Odometry dataset and demonstrate competitive odometry performance. |
| Tasks | Calibration, Simultaneous Localization and Mapping, Visual Odometry |
| Published | 2018-03-08 |
| URL | http://arxiv.org/abs/1803.05850v1 |
| http://arxiv.org/pdf/1803.05850v1.pdf | |
| PWC | https://paperswithcode.com/paper/vision-aided-absolute-trajectory-estimation |
| Repo | |
| Framework | |
Steerable $e$PCA: Rotationally Invariant Exponential Family PCA
| Title | Steerable $e$PCA: Rotationally Invariant Exponential Family PCA |
| Authors | Zhizhen Zhao, Lydia T. Liu, Amit Singer |
| Abstract | In photon-limited imaging, the pixel intensities are affected by photon count noise. Many applications, such as 3-D reconstruction using correlation analysis in X-ray free electron laser (XFEL) single molecule imaging, require an accurate estimation of the covariance of the underlying 2-D clean images. Accurate estimation of the covariance from low-photon count images must take into account that pixel intensities are Poisson distributed, hence the classical sample covariance estimator is sub-optimal. Moreover, in single molecule imaging, including in-plane rotated copies of all images could further improve the accuracy of covariance estimation. In this paper we introduce an efficient and accurate algorithm for covariance matrix estimation of count noise 2-D images, including their uniform planar rotations and possibly reflections. Our procedure, steerable $e$PCA, combines in a novel way two recently introduced innovations. The first is a methodology for principal component analysis (PCA) for Poisson distributions, and more generally, exponential family distributions, called $e$PCA. The second is steerable PCA, a fast and accurate procedure for including all planar rotations for PCA. The resulting principal components are invariant to the rotation and reflection of the input images. We demonstrate the efficiency and accuracy of steerable $e$PCA in numerical experiments involving simulated XFEL datasets and rotated Yale B face data. |
| Tasks | |
| Published | 2018-12-20 |
| URL | https://arxiv.org/abs/1812.08789v3 |
| https://arxiv.org/pdf/1812.08789v3.pdf | |
| PWC | https://paperswithcode.com/paper/steerable-epca |
| Repo | |
| Framework | |
From Known to the Unknown: Transferring Knowledge to Answer Questions about Novel Visual and Semantic Concepts
| Title | From Known to the Unknown: Transferring Knowledge to Answer Questions about Novel Visual and Semantic Concepts |
| Authors | Moshiur R Farazi, Salman H Khan, Nick Barnes |
| Abstract | Current Visual Question Answering (VQA) systems can answer intelligent questions about Known' visual content. However, their performance drops significantly when questions about visually and linguistically Unknown’ concepts are presented during inference (Open-world' scenario). A practical VQA system should be able to deal with novel concepts in real world settings. To address this problem, we propose an exemplar-based approach that transfers learning (i.e., knowledge) from previously Known’ concepts to answer questions about the `Unknown’. We learn a highly discriminative joint embedding space, where visual and semantic features are fused to give a unified representation. Once novel concepts are presented to the model, it looks for the closest match from an exemplar set in the joint embedding space. This auxiliary information is used alongside the given Image-Question pair to refine visual attention in a hierarchical fashion. Since handling the high dimensional exemplars on large datasets can be a significant challenge, we introduce an efficient matching scheme that uses a compact feature description for search and retrieval. To evaluate our model, we propose a new split for VQA, separating Unknown visual and semantic concepts from the training set. Our approach shows significant improvements over state-of-the-art VQA models on the proposed Open-World VQA dataset and standard VQA datasets. | |
| Tasks | Question Answering, Visual Question Answering |
| Published | 2018-11-30 |
| URL | http://arxiv.org/abs/1811.12772v1 |
| http://arxiv.org/pdf/1811.12772v1.pdf | |
| PWC | https://paperswithcode.com/paper/from-known-to-the-unknown-transferring |
| Repo | |
| Framework | |
Overview of Approximate Bayesian Computation
| Title | Overview of Approximate Bayesian Computation |
| Authors | S. A. Sisson, Y. Fan, M. A. Beaumont |
| Abstract | This Chapter, “Overview of Approximate Bayesian Computation”, is to appear as the first chapter in the forthcoming Handbook of Approximate Bayesian Computation (2018). It details the main ideas and concepts behind ABC methods with many examples and illustrations. |
| Tasks | |
| Published | 2018-02-27 |
| URL | http://arxiv.org/abs/1802.09720v1 |
| http://arxiv.org/pdf/1802.09720v1.pdf | |
| PWC | https://paperswithcode.com/paper/overview-of-approximate-bayesian-computation |
| Repo | |
| Framework | |
Community Recovery in a Preferential Attachment Graph
| Title | Community Recovery in a Preferential Attachment Graph |
| Authors | Bruce Hajek, Suryanarayana Sankagiri |
| Abstract | A message passing algorithm is derived for recovering communities within a graph generated by a variation of the Barab'{a}si-Albert preferential attachment model. The estimator is assumed to know the arrival times, or order of attachment, of the vertices. The derivation of the algorithm is based on belief propagation under an independence assumption. Two precursors to the message passing algorithm are analyzed: the first is a degree thresholding (DT) algorithm and the second is an algorithm based on the arrival times of the children (C) of a given vertex, where the children of a given vertex are the vertices that attached to it. Comparison of the performance of the algorithms shows it is beneficial to know the arrival times, not just the number, of the children. The probability of correct classification of a vertex is asymptotically determined by the fraction of vertices arriving before it. Two extensions of Algorithm C are given: the first is based on joint likelihood of the children of a fixed set of vertices; it can sometimes be used to seed the message passing algorithm. The second is the message passing algorithm. Simulation results are given. |
| Tasks | |
| Published | 2018-01-21 |
| URL | http://arxiv.org/abs/1801.06818v5 |
| http://arxiv.org/pdf/1801.06818v5.pdf | |
| PWC | https://paperswithcode.com/paper/community-recovery-in-a-preferential |
| Repo | |
| Framework | |
Community Exploration: From Offline Optimization to Online Learning
| Title | Community Exploration: From Offline Optimization to Online Learning |
| Authors | Xiaowei Chen, Weiran Huang, Wei Chen, John C. S. Lui |
| Abstract | We introduce the community exploration problem that has many real-world applications such as online advertising. In the problem, an explorer allocates limited budget to explore communities so as to maximize the number of members he could meet. We provide a systematic study of the community exploration problem, from offline optimization to online learning. For the offline setting where the sizes of communities are known, we prove that the greedy methods for both of non-adaptive exploration and adaptive exploration are optimal. For the online setting where the sizes of communities are not known and need to be learned from the multi-round explorations, we propose an `upper confidence’ like algorithm that achieves the logarithmic regret bounds. By combining the feedback from different rounds, we can achieve a constant regret bound. | |
| Tasks | |
| Published | 2018-11-13 |
| URL | http://arxiv.org/abs/1811.05134v2 |
| http://arxiv.org/pdf/1811.05134v2.pdf | |
| PWC | https://paperswithcode.com/paper/community-exploration-from-offline |
| Repo | |
| Framework | |
Identifying Corresponding Patches in SAR and Optical Images with a Pseudo-Siamese CNN
| Title | Identifying Corresponding Patches in SAR and Optical Images with a Pseudo-Siamese CNN |
| Authors | Lloyd H. Hughes, Michael Schmitt, Lichao Mou, Yuanyuan Wang, Xiao Xiang Zhu |
| Abstract | In this letter, we propose a pseudo-siamese convolutional neural network (CNN) architecture that enables to solve the task of identifying corresponding patches in very-high-resolution (VHR) optical and synthetic aperture radar (SAR) remote sensing imagery. Using eight convolutional layers each in two parallel network streams, a fully connected layer for the fusion of the features learned in each stream, and a loss function based on binary cross-entropy, we achieve a one-hot indication if two patches correspond or not. The network is trained and tested on an automatically generated dataset that is based on a deterministic alignment of SAR and optical imagery via previously reconstructed and subsequently co-registered 3D point clouds. The satellite images, from which the patches comprising our dataset are extracted, show a complex urban scene containing many elevated objects (i.e. buildings), thus providing one of the most difficult experimental environments. The achieved results show that the network is able to predict corresponding patches with high accuracy, thus indicating great potential for further development towards a generalized multi-sensor key-point matching procedure. Index Terms-synthetic aperture radar (SAR), optical imagery, data fusion, deep learning, convolutional neural networks (CNN), image matching, deep matching |
| Tasks | |
| Published | 2018-01-25 |
| URL | http://arxiv.org/abs/1801.08467v1 |
| http://arxiv.org/pdf/1801.08467v1.pdf | |
| PWC | https://paperswithcode.com/paper/identifying-corresponding-patches-in-sar-and |
| Repo | |
| Framework | |
