Paper Group ANR 554
Dynamic Hand Gesture Recognition for Wearable Devices with Low Complexity Recurrent Neural Networks. Learning Protein Dynamics with Metastable Switching Systems. A simple technique for improving multi-class classification with neural networks. Towards Robust Deep Neural Networks with BANG. A Novel Artificial Fish Swarm Algorithm for Pattern Recogni …
Dynamic Hand Gesture Recognition for Wearable Devices with Low Complexity Recurrent Neural Networks
| Title | Dynamic Hand Gesture Recognition for Wearable Devices with Low Complexity Recurrent Neural Networks |
| Authors | Sungho Shin, Wonyong Sung |
| Abstract | Gesture recognition is a very essential technology for many wearable devices. While previous algorithms are mostly based on statistical methods including the hidden Markov model, we develop two dynamic hand gesture recognition techniques using low complexity recurrent neural network (RNN) algorithms. One is based on video signal and employs a combined structure of a convolutional neural network (CNN) and an RNN. The other uses accelerometer data and only requires an RNN. Fixed-point optimization that quantizes most of the weights into two bits is conducted to optimize the amount of memory size for weight storage and reduce the power consumption in hardware and software based implementations. |
| Tasks | Gesture Recognition, Hand Gesture Recognition, Hand-Gesture Recognition |
| Published | 2016-08-14 |
| URL | http://arxiv.org/abs/1608.04080v1 |
| http://arxiv.org/pdf/1608.04080v1.pdf | |
| PWC | https://paperswithcode.com/paper/dynamic-hand-gesture-recognition-for-wearable |
| Repo | |
| Framework | |
Learning Protein Dynamics with Metastable Switching Systems
| Title | Learning Protein Dynamics with Metastable Switching Systems |
| Authors | Bharath Ramsundar, Vijay S. Pande |
| Abstract | We introduce a machine learning approach for extracting fine-grained representations of protein evolution from molecular dynamics datasets. Metastable switching linear dynamical systems extend standard switching models with a physically-inspired stability constraint. This constraint enables the learning of nuanced representations of protein dynamics that closely match physical reality. We derive an EM algorithm for learning, where the E-step extends the forward-backward algorithm for HMMs and the M-step requires the solution of large biconvex optimization problems. We construct an approximate semidefinite program solver based on the Frank-Wolfe algorithm and use it to solve the M-step. We apply our EM algorithm to learn accurate dynamics from large simulation datasets for the opioid peptide met-enkephalin and the proto-oncogene Src-kinase. Our learned models demonstrate significant improvements in temporal coherence over HMMs and standard switching models for met-enkephalin, and sample transition paths (possibly useful in rational drug design) for Src-kinase. |
| Tasks | |
| Published | 2016-10-05 |
| URL | http://arxiv.org/abs/1610.01642v1 |
| http://arxiv.org/pdf/1610.01642v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-protein-dynamics-with-metastable |
| Repo | |
| Framework | |
A simple technique for improving multi-class classification with neural networks
| Title | A simple technique for improving multi-class classification with neural networks |
| Authors | Thomas Kopinski, Alexander Gepperth, Uwe Handmann |
| Abstract | We present a novel method to perform multi-class pattern classification with neural networks and test it on a challenging 3D hand gesture recognition problem. Our method consists of a standard one-against-all (OAA) classification, followed by another network layer classifying the resulting class scores, possibly augmented by the original raw input vector. This allows the network to disambiguate hard-to-separate classes as the distribution of class scores carries considerable information as well, and is in fact often used for assessing the confidence of a decision. We show that by this approach we are able to significantly boost our results, overall as well as for particular difficult cases, on the hard 10-class gesture classification task. |
| Tasks | Gesture Recognition, Hand Gesture Recognition, Hand-Gesture Recognition |
| Published | 2016-01-06 |
| URL | http://arxiv.org/abs/1601.01157v1 |
| http://arxiv.org/pdf/1601.01157v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-simple-technique-for-improving-multi-class |
| Repo | |
| Framework | |
Towards Robust Deep Neural Networks with BANG
| Title | Towards Robust Deep Neural Networks with BANG |
| Authors | Andras Rozsa, Manuel Gunther, Terrance E. Boult |
| Abstract | Machine learning models, including state-of-the-art deep neural networks, are vulnerable to small perturbations that cause unexpected classification errors. This unexpected lack of robustness raises fundamental questions about their generalization properties and poses a serious concern for practical deployments. As such perturbations can remain imperceptible - the formed adversarial examples demonstrate an inherent inconsistency between vulnerable machine learning models and human perception - some prior work casts this problem as a security issue. Despite the significance of the discovered instabilities and ensuing research, their cause is not well understood and no effective method has been developed to address the problem. In this paper, we present a novel theory to explain why this unpleasant phenomenon exists in deep neural networks. Based on that theory, we introduce a simple, efficient, and effective training approach, Batch Adjusted Network Gradients (BANG), which significantly improves the robustness of machine learning models. While the BANG technique does not rely on any form of data augmentation or the utilization of adversarial images for training, the resultant classifiers are more resistant to adversarial perturbations while maintaining or even enhancing the overall classification performance. |
| Tasks | Data Augmentation |
| Published | 2016-12-01 |
| URL | http://arxiv.org/abs/1612.00138v3 |
| http://arxiv.org/pdf/1612.00138v3.pdf | |
| PWC | https://paperswithcode.com/paper/towards-robust-deep-neural-networks-with-bang |
| Repo | |
| Framework | |
A Novel Artificial Fish Swarm Algorithm for Pattern Recognition with Convex Optimization
| Title | A Novel Artificial Fish Swarm Algorithm for Pattern Recognition with Convex Optimization |
| Authors | Lei Shi, Rui Guo, Yuchen Ma |
| Abstract | Image pattern recognition is an important area in digital image processing. An efficient pattern recognition algorithm should be able to provide correct recognition at a reduced computational time. Off late amongst the machine learning pattern recognition algorithms, Artificial fish swarm algorithm is one of the swarm intelligence optimization algorithms that works based on population and stochastic search. In order to achieve acceptable result, there are many parameters needs to be adjusted in AFSA. Among these parameters, visual and step are very significant in view of the fact that artificial fish basically move based on these parameters. In standard AFSA, these two parameters remain constant until the algorithm termination. Large values of these parameters increase the capability of algorithm in global search, while small values improve the local search ability of the algorithm. In this paper, we empirically study the performance of the AFSA and different approaches to balance between local and global exploration have been tested based on the adaptive modification of visual and step during algorithm execution. The proposed approaches have been evaluated based on the four well-known benchmark functions. Experimental results show considerable positive impact on the performance of AFSA. A Convex optimization has been integrated into the proposed work to have an ideal segmentation of the input image which is a MR brain image. |
| Tasks | |
| Published | 2016-12-01 |
| URL | http://arxiv.org/abs/1612.00125v2 |
| http://arxiv.org/pdf/1612.00125v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-novel-artificial-fish-swarm-algorithm-for |
| Repo | |
| Framework | |
Robust High-Dimensional Linear Regression
| Title | Robust High-Dimensional Linear Regression |
| Authors | Chang Liu, Bo Li, Yevgeniy Vorobeychik, Alina Oprea |
| Abstract | The effectiveness of supervised learning techniques has made them ubiquitous in research and practice. In high-dimensional settings, supervised learning commonly relies on dimensionality reduction to improve performance and identify the most important factors in predicting outcomes. However, the economic importance of learning has made it a natural target for adversarial manipulation of training data, which we term poisoning attacks. Prior approaches to dealing with robust supervised learning rely on strong assumptions about the nature of the feature matrix, such as feature independence and sub-Gaussian noise with low variance. We propose an integrated method for robust regression that relaxes these assumptions, assuming only that the feature matrix can be well approximated by a low-rank matrix. Our techniques integrate improved robust low-rank matrix approximation and robust principle component regression, and yield strong performance guarantees. Moreover, we experimentally show that our methods significantly outperform state of the art both in running time and prediction error. |
| Tasks | Dimensionality Reduction |
| Published | 2016-08-07 |
| URL | http://arxiv.org/abs/1608.02257v2 |
| http://arxiv.org/pdf/1608.02257v2.pdf | |
| PWC | https://paperswithcode.com/paper/robust-high-dimensional-linear-regression |
| Repo | |
| Framework | |
Shape Recognition by Bag of Skeleton-associated Contour Parts
| Title | Shape Recognition by Bag of Skeleton-associated Contour Parts |
| Authors | Wei Shen, Yuan Jiang, Wenjing Gao, Dan Zeng, Xinggang Wang |
| Abstract | Contour and skeleton are two complementary representations for shape recognition. However combining them in a principal way is nontrivial, as they are generally abstracted by different structures (closed string vs graph), respectively. This paper aims at addressing the shape recognition problem by combining contour and skeleton according to the correspondence between them. The correspondence provides a straightforward way to associate skeletal information with a shape contour. More specifically, we propose a new shape descriptor. named Skeleton-associated Shape Context (SSC), which captures the features of a contour fragment associated with skeletal information. Benefited from the association, the proposed shape descriptor provides the complementary geometric information from both contour and skeleton parts, including the spatial distribution and the thickness change along the shape part. To form a meaningful shape feature vector for an overall shape, the Bag of Features framework is applied to the SSC descriptors extracted from it. Finally, the shape feature vector is fed into a linear SVM classifier to recognize the shape. The encouraging experimental results demonstrate that the proposed way to combine contour and skeleton is effective for shape recognition, which achieves the state-of-the-art performances on several standard shape benchmarks. |
| Tasks | |
| Published | 2016-05-20 |
| URL | http://arxiv.org/abs/1605.06417v1 |
| http://arxiv.org/pdf/1605.06417v1.pdf | |
| PWC | https://paperswithcode.com/paper/shape-recognition-by-bag-of-skeleton |
| Repo | |
| Framework | |
Deep Learning Logo Detection with Data Expansion by Synthesising Context
| Title | Deep Learning Logo Detection with Data Expansion by Synthesising Context |
| Authors | Hang Su, Xiatian Zhu, Shaogang Gong |
| Abstract | Logo detection in unconstrained images is challenging, particularly when only very sparse labelled training images are accessible due to high labelling costs. In this work, we describe a model training image synthesising method capable of improving significantly logo detection performance when only a handful of (e.g., 10) labelled training images captured in realistic context are available, avoiding extensive manual labelling costs. Specifically, we design a novel algorithm for generating Synthetic Context Logo (SCL) training images to increase model robustness against unknown background clutters, resulting in superior logo detection performance. For benchmarking model performance, we introduce a new logo detection dataset TopLogo-10 collected from top 10 most popular clothing/wearable brandname logos captured in rich visual context. Extensive comparisons show the advantages of our proposed SCL model over the state-of-the-art alternatives for logo detection using two real-world logo benchmark datasets: FlickrLogo-32 and our new TopLogo-10. |
| Tasks | |
| Published | 2016-12-29 |
| URL | http://arxiv.org/abs/1612.09322v3 |
| http://arxiv.org/pdf/1612.09322v3.pdf | |
| PWC | https://paperswithcode.com/paper/deep-learning-logo-detection-with-data |
| Repo | |
| Framework | |
Simple2Complex: Global Optimization by Gradient Descent
| Title | Simple2Complex: Global Optimization by Gradient Descent |
| Authors | Ming Li |
| Abstract | A method named simple2complex for modeling and training deep neural networks is proposed. Simple2complex train deep neural networks by smoothly adding more and more layers to the shallow networks, as the learning procedure going on, the network is just like growing. Compared with learning by end2end, simple2complex is with less possibility trapping into local minimal, namely, owning ability for global optimization. Cifar10 is used for verifying the superiority of simple2complex. |
| Tasks | |
| Published | 2016-05-02 |
| URL | http://arxiv.org/abs/1605.00404v1 |
| http://arxiv.org/pdf/1605.00404v1.pdf | |
| PWC | https://paperswithcode.com/paper/simple2complex-global-optimization-by |
| Repo | |
| Framework | |
Depth and Reflection Total Variation for Single Image Dehazing
| Title | Depth and Reflection Total Variation for Single Image Dehazing |
| Authors | Wei Wang, Chuanjiang He |
| Abstract | Haze removal has been a very challenging problem due to its ill-posedness, which is more ill-posed if the input data is only a single hazy image. In this paper, we present a new approach for removing haze from a single input image. The proposed method combines the model widely used to describe the formation of a haze image with the assumption in Retinex that an image is the product of the illumination and the reflection. We assume that the depth and reflection functions are spatially piecewise smooth in the model, where the total variation is used for the regularization. The proposed model is defined as a constrained optimization problem, which is solved by an alternating minimization scheme and the fast gradient projection algorithm. Some theoretic analyses are given for the proposed model and algorithm. Finally, numerical examples are presented to demonstrate that our method can restore vivid and contrastive hazy images effectively. |
| Tasks | Image Dehazing, Single Image Dehazing |
| Published | 2016-01-22 |
| URL | http://arxiv.org/abs/1601.05994v1 |
| http://arxiv.org/pdf/1601.05994v1.pdf | |
| PWC | https://paperswithcode.com/paper/depth-and-reflection-total-variation-for |
| Repo | |
| Framework | |
Filter sharing: Efficient learning of parameters for volumetric convolutions
| Title | Filter sharing: Efficient learning of parameters for volumetric convolutions |
| Authors | Rahul Venkataramani, Sheshadri Thiruvenkadam, Prasad Sudhakar, Hariharan Ravishankar, Vivek Vaidya |
| Abstract | Typical convolutional neural networks (CNNs) have several millions of parameters and require a large amount of annotated data to train them. In medical applications where training data is hard to come by, these sophisticated machine learning models are difficult to train. In this paper, we propose a method to reduce the inherent complexity of CNNs during training by exploiting the significant redundancy that is noticed in the learnt CNN filters. Our method relies on finding a small set of filters and mixing coefficients to derive every filter in each convolutional layer at the time of training itself, thereby reducing the number of parameters to be trained. We consider the problem of 3D lung nodule segmentation in CT images and demonstrate the effectiveness of our method in achieving good results with only few training examples. |
| Tasks | Lung Nodule Segmentation |
| Published | 2016-12-08 |
| URL | http://arxiv.org/abs/1612.02575v1 |
| http://arxiv.org/pdf/1612.02575v1.pdf | |
| PWC | https://paperswithcode.com/paper/filter-sharing-efficient-learning-of |
| Repo | |
| Framework | |
Multi-Scale Saliency Detection using Dictionary Learning
| Title | Multi-Scale Saliency Detection using Dictionary Learning |
| Authors | Shubham Pachori |
| Abstract | Saliency detection has drawn a lot of attention of researchers in various fields over the past several years. Saliency is the perceptual quality that makes an object, person to draw the attention of humans at the very sight. Salient object detection in an image has been used centrally in many computational photography and computer vision applications like video compression, object recognition and classification, object segmentation, adaptive content delivery, motion detection, content aware resizing, camouflage images and change blindness images to name a few. We propose a method to detect saliency in the objects using multimodal dictionary learning which has been recently used in classification and image fusion. The multimodal dictionary that we are learning is task driven which gives improved performance over its counterpart (the one which is not task specific). |
| Tasks | Dictionary Learning, Motion Detection, Object Detection, Object Recognition, Saliency Detection, Salient Object Detection, Semantic Segmentation, Video Compression |
| Published | 2016-11-19 |
| URL | http://arxiv.org/abs/1611.06307v3 |
| http://arxiv.org/pdf/1611.06307v3.pdf | |
| PWC | https://paperswithcode.com/paper/multi-scale-saliency-detection-using |
| Repo | |
| Framework | |
Anomaly Detection in Bitcoin Network Using Unsupervised Learning Methods
| Title | Anomaly Detection in Bitcoin Network Using Unsupervised Learning Methods |
| Authors | Thai Pham, Steven Lee |
| Abstract | The problem of anomaly detection has been studied for a long time. In short, anomalies are abnormal or unlikely things. In financial networks, thieves and illegal activities are often anomalous in nature. Members of a network want to detect anomalies as soon as possible to prevent them from harming the network’s community and integrity. Many Machine Learning techniques have been proposed to deal with this problem; some results appear to be quite promising but there is no obvious superior method. In this paper, we consider anomaly detection particular to the Bitcoin transaction network. Our goal is to detect which users and transactions are the most suspicious; in this case, anomalous behavior is a proxy for suspicious behavior. To this end, we use three unsupervised learning methods including k-means clustering, Mahalanobis distance, and Unsupervised Support Vector Machine (SVM) on two graphs generated by the Bitcoin transaction network: one graph has users as nodes, and the other has transactions as nodes. |
| Tasks | Anomaly Detection |
| Published | 2016-11-12 |
| URL | http://arxiv.org/abs/1611.03941v2 |
| http://arxiv.org/pdf/1611.03941v2.pdf | |
| PWC | https://paperswithcode.com/paper/anomaly-detection-in-bitcoin-network-using |
| Repo | |
| Framework | |
On deterministic conditions for subspace clustering under missing data
| Title | On deterministic conditions for subspace clustering under missing data |
| Authors | Wenqi Wang, Shuchin Aeron, Vaneet Aggarwal |
| Abstract | In this paper we present deterministic analysis of sufficient conditions for sparse subspace clustering under missing data, when data is assumed to come from a Union of Subspaces (UoS) model. In this context we consider two cases, namely Case I when all the points are sampled at the same co-ordinates, and Case II when points are sampled at different locations. We show that results for Case I directly follow from several existing results in the literature, while results for Case II are not as straightforward and we provide a set of dual conditions under which, perfect clustering holds true. We provide extensive set of simulation results for clustering as well as completion of data under missing entries, under the UoS model. Our experimental results indicate that in contrast to the full data case, accurate clustering does not imply accurate subspace identification and completion, indicating the natural order of relative hardness of these problems. |
| Tasks | |
| Published | 2016-04-15 |
| URL | http://arxiv.org/abs/1604.04615v1 |
| http://arxiv.org/pdf/1604.04615v1.pdf | |
| PWC | https://paperswithcode.com/paper/on-deterministic-conditions-for-subspace |
| Repo | |
| Framework | |
Predicting the dynamics of 2d objects with a deep residual network
| Title | Predicting the dynamics of 2d objects with a deep residual network |
| Authors | François Fleuret |
| Abstract | We investigate how a residual network can learn to predict the dynamics of interacting shapes purely as an image-to-image regression task. With a simple 2d physics simulator, we generate short sequences composed of rectangles put in motion by applying a pulling force at a point picked at random. The network is trained with a quadratic loss to predict the image of the resulting configuration, given the image of the starting configuration and an image indicating the point of grasping. Experiments show that the network learns to predict accurately the resulting image, which implies in particular that (1) it segments rectangles as distinct components, (2) it infers which one contains the grasping point, (3) it models properly the dynamic of a single rectangle, including the torque, (4) it detects and handles collisions to some extent, and (5) it re-synthesizes properly the entire scene with displaced rectangles. |
| Tasks | |
| Published | 2016-10-13 |
| URL | http://arxiv.org/abs/1610.04032v2 |
| http://arxiv.org/pdf/1610.04032v2.pdf | |
| PWC | https://paperswithcode.com/paper/predicting-the-dynamics-of-2d-objects-with-a |
| Repo | |
| Framework | |
