Paper Group ANR 647
Deep Reinforcement Learning for Autonomous Driving. Harmonic Alignment. Online Markov Decoding: Lower Bounds and Near-Optimal Approximation Algorithms. A Machine-Learning Phase Classification Scheme for Anomaly Detection in Signals with Periodic Characteristics. Large-scale Bisample Learning on ID Versus Spot Face Recognition. Fast Neural Chinese W …
Deep Reinforcement Learning for Autonomous Driving
| Title | Deep Reinforcement Learning for Autonomous Driving |
| Authors | Sen Wang, Daoyuan Jia, Xinshuo Weng |
| Abstract | Reinforcement learning has steadily improved and outperform human in lots of traditional games since the resurgence of deep neural network. However, these success is not easy to be copied to autonomous driving because the state spaces in real world are extreme complex and action spaces are continuous and fine control is required. Moreover, the autonomous driving vehicles must also keep functional safety under the complex environments. To deal with these challenges, we first adopt the deep deterministic policy gradient (DDPG) algorithm, which has the capacity to handle complex state and action spaces in continuous domain. We then choose The Open Racing Car Simulator (TORCS) as our environment to avoid physical damage. Meanwhile, we select a set of appropriate sensor information from TORCS and design our own rewarder. In order to fit DDPG algorithm to TORCS, we design our network architecture for both actor and critic inside DDPG paradigm. To demonstrate the effectiveness of our model, We evaluate on different modes in TORCS and show both quantitative and qualitative results. |
| Tasks | Autonomous Driving |
| Published | 2018-11-28 |
| URL | https://arxiv.org/abs/1811.11329v3 |
| https://arxiv.org/pdf/1811.11329v3.pdf | |
| PWC | https://paperswithcode.com/paper/deep-reinforcement-learning-for-autonomous |
| Repo | |
| Framework | |
Harmonic Alignment
| Title | Harmonic Alignment |
| Authors | Jay S. Stanley III, Scott Gigante, Guy Wolf, Smita Krishnaswamy |
| Abstract | We propose a novel framework for combining datasets via alignment of their intrinsic geometry. This alignment can be used to fuse data originating from disparate modalities, or to correct batch effects while preserving intrinsic data structure. Importantly, we do not assume any pointwise correspondence between datasets, but instead rely on correspondence between a (possibly unknown) subset of data features. We leverage this assumption to construct an isometric alignment between the data. This alignment is obtained by relating the expansion of data features in harmonics derived from diffusion operators defined over each dataset. These expansions encode each feature as a function of the data geometry. We use this to relate the diffusion coordinates of each dataset through our assumption of partial feature correspondence. Then, a unified diffusion geometry is constructed over the aligned data, which can also be used to correct the original data measurements. We demonstrate our method on several datasets, showing in particular its effectiveness in biological applications including fusion of single-cell RNA sequencing (scRNA-seq) and single-cell ATAC sequencing (scATAC-seq) data measured on the same population of cells, and removal of batch effect between biological samples. |
| Tasks | |
| Published | 2018-09-30 |
| URL | https://arxiv.org/abs/1810.00386v4 |
| https://arxiv.org/pdf/1810.00386v4.pdf | |
| PWC | https://paperswithcode.com/paper/manifold-alignment-with-feature |
| Repo | |
| Framework | |
Online Markov Decoding: Lower Bounds and Near-Optimal Approximation Algorithms
| Title | Online Markov Decoding: Lower Bounds and Near-Optimal Approximation Algorithms |
| Authors | Vikas K. Garg, Tamar Pichkhadze |
| Abstract | We resolve the fundamental problem of online decoding with general $n^{th}$ order ergodic Markov chain models. Specifically, we provide deterministic and randomized algorithms whose performance is close to that of the optimal offline algorithm even when latency is small. Our algorithms admit efficient implementation via dynamic programs, and readily extend to (adversarial) non-stationary or time-varying settings. We also establish lower bounds for online methods under latency constraints in both deterministic and randomized settings, and show that no online algorithm can perform significantly better than our algorithms. Empirically, just with latency one, our algorithm outperforms the online step algorithm by over 30% in terms of decoding agreement with the optimal algorithm on genome sequence data. |
| Tasks | |
| Published | 2018-10-16 |
| URL | https://arxiv.org/abs/1810.07301v2 |
| https://arxiv.org/pdf/1810.07301v2.pdf | |
| PWC | https://paperswithcode.com/paper/peek-search-near-optimal-online-markov |
| Repo | |
| Framework | |
A Machine-Learning Phase Classification Scheme for Anomaly Detection in Signals with Periodic Characteristics
| Title | A Machine-Learning Phase Classification Scheme for Anomaly Detection in Signals with Periodic Characteristics |
| Authors | Lia Ahrens, Julian Ahrens, Hans D. Schotten |
| Abstract | In this paper we propose a novel machine-learning method for anomaly detection applicable to data with periodic characteristics where randomly varying period lengths are explicitly allowed. A multi-dimensional time series analysis is conducted by training a data-adapted classifier consisting of deep convolutional neural networks performing phase classification. The entire algorithm including data pre-processing, period detection, segmentation, and even dynamic adjustment of the neural networks is implemented for fully automatic execution. The proposed method is evaluated on three example datasets from the areas of cardiology, intrusion detection, and signal processing, presenting reasonable performance. |
| Tasks | Anomaly Detection, Intrusion Detection, Time Series, Time Series Analysis |
| Published | 2018-11-29 |
| URL | http://arxiv.org/abs/1811.12119v2 |
| http://arxiv.org/pdf/1811.12119v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-machine-learning-phase-classification |
| Repo | |
| Framework | |
Large-scale Bisample Learning on ID Versus Spot Face Recognition
| Title | Large-scale Bisample Learning on ID Versus Spot Face Recognition |
| Authors | Xiangyu Zhu, Hao Liu, Zhen Lei, Hailin Shi, Fan Yang, Dong Yi, Guojun Qi, Stan Z. Li |
| Abstract | In real-world face recognition applications, there is a tremendous amount of data with two images for each person. One is an ID photo for face enrollment, and the other is a probe photo captured on spot. Most existing methods are designed for training data with limited breadth (a relatively small number of classes) and sufficient depth (many samples for each class). They would meet great challenges on ID versus Spot (IvS) data, including the under-represented intra-class variations and an excessive demand on computing devices. In this paper, we propose a deep learning based large-scale bisample learning (LBL) method for IvS face recognition. To tackle the bisample problem with only two samples for each class, a classification-verification-classification (CVC) training strategy is proposed to progressively enhance the IvS performance. Besides, a dominant prototype softmax (DP-softmax) is incorporated to make the deep learning scalable on large-scale classes. We conduct LBL on a IvS face dataset with more than two million identities. Experimental results show the proposed method achieves superior performance to previous ones, validating the effectiveness of LBL on IvS face recognition. |
| Tasks | Face Recognition |
| Published | 2018-06-08 |
| URL | http://arxiv.org/abs/1806.03018v3 |
| http://arxiv.org/pdf/1806.03018v3.pdf | |
| PWC | https://paperswithcode.com/paper/large-scale-bisample-learning-on-id-versus |
| Repo | |
| Framework | |
Fast Neural Chinese Word Segmentation for Long Sentences
| Title | Fast Neural Chinese Word Segmentation for Long Sentences |
| Authors | Sufeng Duan, Jiangtong Li, Hai Zhao |
| Abstract | Rapidly developed neural models have achieved competitive performance in Chinese word segmentation (CWS) as their traditional counterparts. However, most of methods encounter the computational inefficiency especially for long sentences because of the increasing model complexity and slower decoders. This paper presents a simple neural segmenter which directly labels the gap existence between adjacent characters to alleviate the existing drawback. Our segmenter is fully end-to-end and capable of performing segmentation very fast. We also show a performance difference with different tag sets. The experiments show that our segmenter can provide comparable performance with state-of-the-art. |
| Tasks | Chinese Word Segmentation |
| Published | 2018-11-06 |
| URL | http://arxiv.org/abs/1811.02602v2 |
| http://arxiv.org/pdf/1811.02602v2.pdf | |
| PWC | https://paperswithcode.com/paper/fast-neural-chinese-word-segmentation-for |
| Repo | |
| Framework | |
AliMe Assist: An Intelligent Assistant for Creating an Innovative E-commerce Experience
| Title | AliMe Assist: An Intelligent Assistant for Creating an Innovative E-commerce Experience |
| Authors | Feng-Lin Li, Minghui Qiu, Haiqing Chen, Xiongwei Wang, Xing Gao, Jun Huang, Juwei Ren, Zhongzhou Zhao, Weipeng Zhao, Lei Wang, Guwei Jin, Wei Chu |
| Abstract | We present AliMe Assist, an intelligent assistant designed for creating an innovative online shopping experience in E-commerce. Based on question answering (QA), AliMe Assist offers assistance service, customer service, and chatting service. It is able to take voice and text input, incorporate context to QA, and support multi-round interaction. Currently, it serves millions of customer questions per day and is able to address 85% of them. In this paper, we demonstrate the system, present the underlying techniques, and share our experience in dealing with real-world QA in the E-commerce field. |
| Tasks | Question Answering |
| Published | 2018-01-12 |
| URL | http://arxiv.org/abs/1801.05032v1 |
| http://arxiv.org/pdf/1801.05032v1.pdf | |
| PWC | https://paperswithcode.com/paper/alime-assist-an-intelligent-assistant-for |
| Repo | |
| Framework | |
Teaching Inverse Reinforcement Learners via Features and Demonstrations
| Title | Teaching Inverse Reinforcement Learners via Features and Demonstrations |
| Authors | Luis Haug, Sebastian Tschiatschek, Adish Singla |
| Abstract | Learning near-optimal behaviour from an expert’s demonstrations typically relies on the assumption that the learner knows the features that the true reward function depends on. In this paper, we study the problem of learning from demonstrations in the setting where this is not the case, i.e., where there is a mismatch between the worldviews of the learner and the expert. We introduce a natural quantity, the teaching risk, which measures the potential suboptimality of policies that look optimal to the learner in this setting. We show that bounds on the teaching risk guarantee that the learner is able to find a near-optimal policy using standard algorithms based on inverse reinforcement learning. Based on these findings, we suggest a teaching scheme in which the expert can decrease the teaching risk by updating the learner’s worldview, and thus ultimately enable her to find a near-optimal policy. |
| Tasks | |
| Published | 2018-10-21 |
| URL | http://arxiv.org/abs/1810.08926v4 |
| http://arxiv.org/pdf/1810.08926v4.pdf | |
| PWC | https://paperswithcode.com/paper/teaching-inverse-reinforcement-learners-via |
| Repo | |
| Framework | |
Mining Illegal Insider Trading of Stocks: A Proactive Approach
| Title | Mining Illegal Insider Trading of Stocks: A Proactive Approach |
| Authors | Sheikh Rabiul Islam, Sheikh Khaled Ghafoor, William Eberle |
| Abstract | Illegal insider trading of stocks is based on releasing non-public information (e.g., new product launch, quarterly financial report, acquisition or merger plan) before the information is made public. Detecting illegal insider trading is difficult due to the complex, nonlinear, and non-stationary nature of the stock market. In this work, we present an approach that detects and predicts illegal insider trading proactively from large heterogeneous sources of structured and unstructured data using a deep-learning based approach combined with discrete signal processing on the time series data. In addition, we use a tree-based approach that visualizes events and actions to aid analysts in their understanding of large amounts of unstructured data. Using existing data, we have discovered that our approach has a good success rate in detecting illegal insider trading patterns. |
| Tasks | Time Series |
| Published | 2018-07-02 |
| URL | http://arxiv.org/abs/1807.00939v3 |
| http://arxiv.org/pdf/1807.00939v3.pdf | |
| PWC | https://paperswithcode.com/paper/mining-illegal-insider-trading-of-stocks-a |
| Repo | |
| Framework | |
Devon: Deformable Volume Network for Learning Optical Flow
| Title | Devon: Deformable Volume Network for Learning Optical Flow |
| Authors | Yao Lu, Jack Valmadre, Heng Wang, Juho Kannala, Mehrtash Harandi, Philip H. S. Torr |
| Abstract | State-of-the-art neural network models estimate large displacement optical flow in multi-resolution and use warping to propagate the estimation between two resolutions. Despite their impressive results, it is known that there are two problems with the approach. First, the multi-resolution estimation of optical flow fails in situations where small objects move fast. Second, warping creates artifacts when occlusion or dis-occlusion happens. In this paper, we propose a new neural network module, Deformable Cost Volume, which alleviates the two problems. Based on this module, we designed the Deformable Volume Network (Devon) which can estimate multi-scale optical flow in a single high resolution. Experiments show Devon is more suitable in handling small objects moving fast and achieves comparable results to the state-of-the-art methods in public benchmarks. |
| Tasks | Optical Flow Estimation |
| Published | 2018-02-20 |
| URL | http://arxiv.org/abs/1802.07351v2 |
| http://arxiv.org/pdf/1802.07351v2.pdf | |
| PWC | https://paperswithcode.com/paper/devon-deformable-volume-network-for-learning |
| Repo | |
| Framework | |
Load Balanced GANs for Multi-view Face Image Synthesis
| Title | Load Balanced GANs for Multi-view Face Image Synthesis |
| Authors | Jie Cao, Yibo Hu, Bing Yu, Ran He, Zhenan Sun |
| Abstract | Multi-view face synthesis from a single image is an ill-posed problem and often suffers from serious appearance distortion. Producing photo-realistic and identity preserving multi-view results is still a not well defined synthesis problem. This paper proposes Load Balanced Generative Adversarial Networks (LB-GAN) to precisely rotate the yaw angle of an input face image to any specified angle. LB-GAN decomposes the challenging synthesis problem into two well constrained subtasks that correspond to a face normalizer and a face editor respectively. The normalizer first frontalizes an input image, and then the editor rotates the frontalized image to a desired pose guided by a remote code. In order to generate photo-realistic local details, the normalizer and the editor are trained in a two-stage manner and regulated by a conditional self-cycle loss and an attention based L2 loss. Exhaustive experiments on controlled and uncontrolled environments demonstrate that the proposed method not only improves the visual realism of multi-view synthetic images, but also preserves identity information well. |
| Tasks | Face Generation, Image Generation |
| Published | 2018-02-21 |
| URL | http://arxiv.org/abs/1802.07447v2 |
| http://arxiv.org/pdf/1802.07447v2.pdf | |
| PWC | https://paperswithcode.com/paper/load-balanced-gans-for-multi-view-face-image |
| Repo | |
| Framework | |
A real-time decision support system for bridge management based on the rules generalized by CART decision tree and SMO algorithms
| Title | A real-time decision support system for bridge management based on the rules generalized by CART decision tree and SMO algorithms |
| Authors | Shadi Abpeykar, Mehdi Ghatee |
| Abstract | Under dynamic conditions on bridges, we need a real-time management. To this end, this paper presents a rule-based decision support system in which the necessary rules are extracted from simulation results made by Aimsun traffic micro-simulation software. Then, these rules are generalized by the aid of fuzzy rule generation algorithms. Then, they are trained by a set of supervised and the unsupervised learning algorithms to get an ability to make decision in real cases. As a pilot case study, Nasr Bridge in Tehran is simulated in Aimsun and WEKA data mining software is used to execute the learning algorithms. Based on this experiment, the accuracy of the supervised algorithms to generalize the rules is greater than 80%. In addition, CART decision tree and sequential minimal optimization (SMO) provides 100% accuracy for normal data and these algorithms are so reliable for crisis management on bridge. This means that, it is possible to use such machine learning methods to manage bridges in the real-time conditions. |
| Tasks | |
| Published | 2018-03-04 |
| URL | http://arxiv.org/abs/1803.01412v2 |
| http://arxiv.org/pdf/1803.01412v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-real-time-decision-support-system-for |
| Repo | |
| Framework | |
A Neural Embeddings Approach for Detecting Mobile Counterfeit Apps
| Title | A Neural Embeddings Approach for Detecting Mobile Counterfeit Apps |
| Authors | Jathushan Rajasegaran, Suranga Seneviratne, Guillaume Jourjon |
| Abstract | Counterfeit apps impersonate existing popular apps in attempts to misguide users to install them for various reasons such as collecting personal information, spreading malware, or simply to increase their advertisement revenue. Many counterfeits can be identified once installed, however even a tech-savvy user may struggle to detect them before installation as app icons and descriptions can be quite similar to the original app. To this end, this paper proposes to use neural embeddings generated by state-of-the-art convolutional neural networks (CNNs) to measure the similarity between images. Our results show that for the problem of counterfeit detection a novel approach of using style embeddings given by the Gram matrix of CNN filter responses outperforms baseline methods such as content embeddings and SIFT features. We show that further performance increases can be achieved by combining style embeddings with content embeddings. We present an analysis of approximately 1.2 million apps from Google Play Store and identify a set of potential counterfeits for top-1,000 apps. Under a conservative assumption, we were able to find 139 apps that contain malware in a set of 6,880 apps that showed high visual similarity to one of the top-1,000 apps in Google Play Store. |
| Tasks | |
| Published | 2018-04-26 |
| URL | http://arxiv.org/abs/1804.09882v1 |
| http://arxiv.org/pdf/1804.09882v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-neural-embeddings-approach-for-detecting |
| Repo | |
| Framework | |
Minimax Estimation of Quadratic Fourier Functionals
| Title | Minimax Estimation of Quadratic Fourier Functionals |
| Authors | Shashank Singh, Bharath K. Sriperumbudur, Barnabás Póczos |
| Abstract | We study estimation of (semi-)inner products between two nonparametric probability distributions, given IID samples from each distribution. These products include relatively well-studied classical $\mathcal{L}^2$ and Sobolev inner products, as well as those induced by translation-invariant reproducing kernels, for which we believe our results are the first. We first propose estimators for these quantities, and the induced (semi)norms and (pseudo)metrics. We then prove non-asymptotic upper bounds on their mean squared error, in terms of weights both of the inner product and of the two distributions, in the Fourier basis. Finally, we prove minimax lower bounds that imply rate-optimality of the proposed estimators over Fourier ellipsoids. |
| Tasks | |
| Published | 2018-03-30 |
| URL | http://arxiv.org/abs/1803.11451v2 |
| http://arxiv.org/pdf/1803.11451v2.pdf | |
| PWC | https://paperswithcode.com/paper/minimax-estimation-of-quadratic-fourier |
| Repo | |
| Framework | |
Brand > Logo: Visual Analysis of Fashion Brands
| Title | Brand > Logo: Visual Analysis of Fashion Brands |
| Authors | M. Hadi Kiapour, Robinson Piramuthu |
| Abstract | While lots of people may think branding begins and ends with a logo, fashion brands communicate their uniqueness through a wide range of visual cues such as color, patterns and shapes. In this work, we analyze learned visual representations by deep networks that are trained to recognize fashion brands. In particular, the activation strength and extent of neurons are studied to provide interesting insights about visual brand expressions. The proposed method identifies where a brand stands in the spectrum of branding strategy, i.e., from trademark-emblazoned goods with bold logos to implicit no logo marketing. By quantifying attention maps, we are able to interpret the visual characteristics of a brand present in a single image and model the general design direction of a brand as a whole. We further investigate versatility of neurons and discover “specialists” that are highly brand-specific and “generalists” that detect diverse visual features. A human experiment based on three main visual scenarios of fashion brands is conducted to verify the alignment of our quantitative measures with the human perception of brands. This paper demonstrate how deep networks go beyond logos in order to recognize clothing brands in an image. |
| Tasks | |
| Published | 2018-10-23 |
| URL | http://arxiv.org/abs/1810.09941v1 |
| http://arxiv.org/pdf/1810.09941v1.pdf | |
| PWC | https://paperswithcode.com/paper/brand-logo-visual-analysis-of-fashion-brands |
| Repo | |
| Framework | |
