Paper Group AWR 151
A Semantics-Based Measure of Emoji Similarity. Deep & Cross Network for Ad Click Predictions. Convolutional Recurrent Neural Networks for Electrocardiogram Classification. Analyzing the Robustness of Nearest Neighbors to Adversarial Examples. Multiple-Human Parsing in the Wild. AirSim: High-Fidelity Visual and Physical Simulation for Autonomous Veh …
A Semantics-Based Measure of Emoji Similarity
| Title | A Semantics-Based Measure of Emoji Similarity |
| Authors | Sanjaya Wijeratne, Lakshika Balasuriya, Amit Sheth, Derek Doran |
| Abstract | Emoji have grown to become one of the most important forms of communication on the web. With its widespread use, measuring the similarity of emoji has become an important problem for contemporary text processing since it lies at the heart of sentiment analysis, search, and interface design tasks. This paper presents a comprehensive analysis of the semantic similarity of emoji through embedding models that are learned over machine-readable emoji meanings in the EmojiNet knowledge base. Using emoji descriptions, emoji sense labels and emoji sense definitions, and with different training corpora obtained from Twitter and Google News, we develop and test multiple embedding models to measure emoji similarity. To evaluate our work, we create a new dataset called EmoSim508, which assigns human-annotated semantic similarity scores to a set of 508 carefully selected emoji pairs. After validation with EmoSim508, we present a real-world use-case of our emoji embedding models using a sentiment analysis task and show that our models outperform the previous best-performing emoji embedding model on this task. The EmoSim508 dataset and our emoji embedding models are publicly released with this paper and can be downloaded from http://emojinet.knoesis.org/. |
| Tasks | Semantic Similarity, Semantic Textual Similarity, Sentiment Analysis |
| Published | 2017-07-14 |
| URL | http://arxiv.org/abs/1707.04653v1 |
| http://arxiv.org/pdf/1707.04653v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-semantics-based-measure-of-emoji-similarity |
| Repo | https://github.com/hougrammer/emoji_project |
| Framework | tf |
Deep & Cross Network for Ad Click Predictions
| Title | Deep & Cross Network for Ad Click Predictions |
| Authors | Ruoxi Wang, Bin Fu, Gang Fu, Mingliang Wang |
| Abstract | Feature engineering has been the key to the success of many prediction models. However, the process is non-trivial and often requires manual feature engineering or exhaustive searching. DNNs are able to automatically learn feature interactions; however, they generate all the interactions implicitly, and are not necessarily efficient in learning all types of cross features. In this paper, we propose the Deep & Cross Network (DCN) which keeps the benefits of a DNN model, and beyond that, it introduces a novel cross network that is more efficient in learning certain bounded-degree feature interactions. In particular, DCN explicitly applies feature crossing at each layer, requires no manual feature engineering, and adds negligible extra complexity to the DNN model. Our experimental results have demonstrated its superiority over the state-of-art algorithms on the CTR prediction dataset and dense classification dataset, in terms of both model accuracy and memory usage. |
| Tasks | Click-Through Rate Prediction, Feature Engineering |
| Published | 2017-08-17 |
| URL | http://arxiv.org/abs/1708.05123v1 |
| http://arxiv.org/pdf/1708.05123v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-cross-network-for-ad-click-predictions |
| Repo | https://github.com/Snail110/recsys |
| Framework | tf |
Convolutional Recurrent Neural Networks for Electrocardiogram Classification
| Title | Convolutional Recurrent Neural Networks for Electrocardiogram Classification |
| Authors | Martin Zihlmann, Dmytro Perekrestenko, Michael Tschannen |
| Abstract | We propose two deep neural network architectures for classification of arbitrary-length electrocardiogram (ECG) recordings and evaluate them on the atrial fibrillation (AF) classification data set provided by the PhysioNet/CinC Challenge 2017. The first architecture is a deep convolutional neural network (CNN) with averaging-based feature aggregation across time. The second architecture combines convolutional layers for feature extraction with long-short term memory (LSTM) layers for temporal aggregation of features. As a key ingredient of our training procedure we introduce a simple data augmentation scheme for ECG data and demonstrate its effectiveness in the AF classification task at hand. The second architecture was found to outperform the first one, obtaining an $F_1$ score of $82.1$% on the hidden challenge testing set. |
| Tasks | Data Augmentation |
| Published | 2017-10-17 |
| URL | http://arxiv.org/abs/1710.06122v2 |
| http://arxiv.org/pdf/1710.06122v2.pdf | |
| PWC | https://paperswithcode.com/paper/convolutional-recurrent-neural-networks-for |
| Repo | https://github.com/yruffiner/ecg-classification |
| Framework | tf |
Analyzing the Robustness of Nearest Neighbors to Adversarial Examples
| Title | Analyzing the Robustness of Nearest Neighbors to Adversarial Examples |
| Authors | Yizhen Wang, Somesh Jha, Kamalika Chaudhuri |
| Abstract | Motivated by safety-critical applications, test-time attacks on classifiers via adversarial examples has recently received a great deal of attention. However, there is a general lack of understanding on why adversarial examples arise; whether they originate due to inherent properties of data or due to lack of training samples remains ill-understood. In this work, we introduce a theoretical framework analogous to bias-variance theory for understanding these effects. We use our framework to analyze the robustness of a canonical non-parametric classifier - the k-nearest neighbors. Our analysis shows that its robustness properties depend critically on the value of k - the classifier may be inherently non-robust for small k, but its robustness approaches that of the Bayes Optimal classifier for fast-growing k. We propose a novel modified 1-nearest neighbor classifier, and guarantee its robustness in the large sample limit. Our experiments suggest that this classifier may have good robustness properties even for reasonable data set sizes. |
| Tasks | |
| Published | 2017-06-13 |
| URL | https://arxiv.org/abs/1706.03922v6 |
| https://arxiv.org/pdf/1706.03922v6.pdf | |
| PWC | https://paperswithcode.com/paper/analyzing-the-robustness-of-nearest-neighbors |
| Repo | https://github.com/EricYizhenWang/robust_nn_icml |
| Framework | tf |
Multiple-Human Parsing in the Wild
| Title | Multiple-Human Parsing in the Wild |
| Authors | Jianshu Li, Jian Zhao, Yunchao Wei, Congyan Lang, Yidong Li, Terence Sim, Shuicheng Yan, Jiashi Feng |
| Abstract | Human parsing is attracting increasing research attention. In this work, we aim to push the frontier of human parsing by introducing the problem of multi-human parsing in the wild. Existing works on human parsing mainly tackle single-person scenarios, which deviates from real-world applications where multiple persons are present simultaneously with interaction and occlusion. To address the multi-human parsing problem, we introduce a new multi-human parsing (MHP) dataset and a novel multi-human parsing model named MH-Parser. The MHP dataset contains multiple persons captured in real-world scenes with pixel-level fine-grained semantic annotations in an instance-aware setting. The MH-Parser generates global parsing maps and person instance masks simultaneously in a bottom-up fashion with the help of a new Graph-GAN model. We envision that the MHP dataset will serve as a valuable data resource to develop new multi-human parsing models, and the MH-Parser offers a strong baseline to drive future research for multi-human parsing in the wild. |
| Tasks | Human Parsing, Multi-Human Parsing |
| Published | 2017-05-19 |
| URL | http://arxiv.org/abs/1705.07206v2 |
| http://arxiv.org/pdf/1705.07206v2.pdf | |
| PWC | https://paperswithcode.com/paper/multiple-human-parsing-in-the-wild |
| Repo | https://github.com/ZhaoJ9014/Multi-Human-Parsing |
| Framework | tf |
AirSim: High-Fidelity Visual and Physical Simulation for Autonomous Vehicles
| Title | AirSim: High-Fidelity Visual and Physical Simulation for Autonomous Vehicles |
| Authors | Shital Shah, Debadeepta Dey, Chris Lovett, Ashish Kapoor |
| Abstract | Developing and testing algorithms for autonomous vehicles in real world is an expensive and time consuming process. Also, in order to utilize recent advances in machine intelligence and deep learning we need to collect a large amount of annotated training data in a variety of conditions and environments. We present a new simulator built on Unreal Engine that offers physically and visually realistic simulations for both of these goals. Our simulator includes a physics engine that can operate at a high frequency for real-time hardware-in-the-loop (HITL) simulations with support for popular protocols (e.g. MavLink). The simulator is designed from the ground up to be extensible to accommodate new types of vehicles, hardware platforms and software protocols. In addition, the modular design enables various components to be easily usable independently in other projects. We demonstrate the simulator by first implementing a quadrotor as an autonomous vehicle and then experimentally comparing the software components with real-world flights. |
| Tasks | Autonomous Vehicles |
| Published | 2017-05-15 |
| URL | http://arxiv.org/abs/1705.05065v2 |
| http://arxiv.org/pdf/1705.05065v2.pdf | |
| PWC | https://paperswithcode.com/paper/airsim-high-fidelity-visual-and-physical |
| Repo | https://github.com/Microsoft/AirSim |
| Framework | tf |
Local Communication Protocols for Learning Complex Swarm Behaviors with Deep Reinforcement Learning
| Title | Local Communication Protocols for Learning Complex Swarm Behaviors with Deep Reinforcement Learning |
| Authors | Maximilian Hüttenrauch, Adrian Šošić, Gerhard Neumann |
| Abstract | Swarm systems constitute a challenging problem for reinforcement learning (RL) as the algorithm needs to learn decentralized control policies that can cope with limited local sensing and communication abilities of the agents. While it is often difficult to directly define the behavior of the agents, simple communication protocols can be defined more easily using prior knowledge about the given task. In this paper, we propose a number of simple communication protocols that can be exploited by deep reinforcement learning to find decentralized control policies in a multi-robot swarm environment. The protocols are based on histograms that encode the local neighborhood relations of the agents and can also transmit task-specific information, such as the shortest distance and direction to a desired target. In our framework, we use an adaptation of Trust Region Policy Optimization to learn complex collaborative tasks, such as formation building and building a communication link. We evaluate our findings in a simulated 2D-physics environment, and compare the implications of different communication protocols. |
| Tasks | |
| Published | 2017-09-21 |
| URL | http://arxiv.org/abs/1709.07224v2 |
| http://arxiv.org/pdf/1709.07224v2.pdf | |
| PWC | https://paperswithcode.com/paper/local-communication-protocols-for-learning |
| Repo | https://github.com/nsrishankar/rl_swarm_papers |
| Framework | none |
Hidden Physics Models: Machine Learning of Nonlinear Partial Differential Equations
| Title | Hidden Physics Models: Machine Learning of Nonlinear Partial Differential Equations |
| Authors | Maziar Raissi, George Em Karniadakis |
| Abstract | While there is currently a lot of enthusiasm about “big data”, useful data is usually “small” and expensive to acquire. In this paper, we present a new paradigm of learning partial differential equations from {\em small} data. In particular, we introduce \emph{hidden physics models}, which are essentially data-efficient learning machines capable of leveraging the underlying laws of physics, expressed by time dependent and nonlinear partial differential equations, to extract patterns from high-dimensional data generated from experiments. The proposed methodology may be applied to the problem of learning, system identification, or data-driven discovery of partial differential equations. Our framework relies on Gaussian processes, a powerful tool for probabilistic inference over functions, that enables us to strike a balance between model complexity and data fitting. The effectiveness of the proposed approach is demonstrated through a variety of canonical problems, spanning a number of scientific domains, including the Navier-Stokes, Schr"odinger, Kuramoto-Sivashinsky, and time dependent linear fractional equations. The methodology provides a promising new direction for harnessing the long-standing developments of classical methods in applied mathematics and mathematical physics to design learning machines with the ability to operate in complex domains without requiring large quantities of data. |
| Tasks | Gaussian Processes |
| Published | 2017-08-02 |
| URL | http://arxiv.org/abs/1708.00588v2 |
| http://arxiv.org/pdf/1708.00588v2.pdf | |
| PWC | https://paperswithcode.com/paper/hidden-physics-models-machine-learning-of |
| Repo | https://github.com/maziarraissi/HPM |
| Framework | none |
Shift: A Zero FLOP, Zero Parameter Alternative to Spatial Convolutions
| Title | Shift: A Zero FLOP, Zero Parameter Alternative to Spatial Convolutions |
| Authors | Bichen Wu, Alvin Wan, Xiangyu Yue, Peter Jin, Sicheng Zhao, Noah Golmant, Amir Gholaminejad, Joseph Gonzalez, Kurt Keutzer |
| Abstract | Neural networks rely on convolutions to aggregate spatial information. However, spatial convolutions are expensive in terms of model size and computation, both of which grow quadratically with respect to kernel size. In this paper, we present a parameter-free, FLOP-free “shift” operation as an alternative to spatial convolutions. We fuse shifts and point-wise convolutions to construct end-to-end trainable shift-based modules, with a hyperparameter characterizing the tradeoff between accuracy and efficiency. To demonstrate the operation’s efficacy, we replace ResNet’s 3x3 convolutions with shift-based modules for improved CIFAR10 and CIFAR100 accuracy using 60% fewer parameters; we additionally demonstrate the operation’s resilience to parameter reduction on ImageNet, outperforming ResNet family members. We finally show the shift operation’s applicability across domains, achieving strong performance with fewer parameters on classification, face verification and style transfer. |
| Tasks | Face Verification, Image Classification, Style Transfer |
| Published | 2017-11-22 |
| URL | http://arxiv.org/abs/1711.08141v2 |
| http://arxiv.org/pdf/1711.08141v2.pdf | |
| PWC | https://paperswithcode.com/paper/shift-a-zero-flop-zero-parameter-alternative |
| Repo | https://github.com/DeadAt0m/ActiveSparseShifts-PyTorch |
| Framework | pytorch |
Recurrent Neural Network Language Models for Open Vocabulary Event-Level Cyber Anomaly Detection
| Title | Recurrent Neural Network Language Models for Open Vocabulary Event-Level Cyber Anomaly Detection |
| Authors | Aaron Tuor, Ryan Baerwolf, Nicolas Knowles, Brian Hutchinson, Nicole Nichols, Rob Jasper |
| Abstract | Automated analysis methods are crucial aids for monitoring and defending a network to protect the sensitive or confidential data it hosts. This work introduces a flexible, powerful, and unsupervised approach to detecting anomalous behavior in computer and network logs, one that largely eliminates domain-dependent feature engineering employed by existing methods. By treating system logs as threads of interleaved “sentences” (event log lines) to train online unsupervised neural network language models, our approach provides an adaptive model of normal network behavior. We compare the effectiveness of both standard and bidirectional recurrent neural network language models at detecting malicious activity within network log data. Extending these models, we introduce a tiered recurrent architecture, which provides context by modeling sequences of users’ actions over time. Compared to Isolation Forest and Principal Components Analysis, two popular anomaly detection algorithms, we observe superior performance on the Los Alamos National Laboratory Cyber Security dataset. For log-line-level red team detection, our best performing character-based model provides test set area under the receiver operator characteristic curve of 0.98, demonstrating the strong fine-grained anomaly detection performance of this approach on open vocabulary logging sources. |
| Tasks | Anomaly Detection, Feature Engineering |
| Published | 2017-12-02 |
| URL | http://arxiv.org/abs/1712.00557v1 |
| http://arxiv.org/pdf/1712.00557v1.pdf | |
| PWC | https://paperswithcode.com/paper/recurrent-neural-network-language-models-for |
| Repo | https://github.com/pnnl/safekit |
| Framework | tf |
Socially Aware Motion Planning with Deep Reinforcement Learning
| Title | Socially Aware Motion Planning with Deep Reinforcement Learning |
| Authors | Yu Fan Chen, Michael Everett, Miao Liu, Jonathan P. How |
| Abstract | For robotic vehicles to navigate safely and efficiently in pedestrian-rich environments, it is important to model subtle human behaviors and navigation rules (e.g., passing on the right). However, while instinctive to humans, socially compliant navigation is still difficult to quantify due to the stochasticity in people’s behaviors. Existing works are mostly focused on using feature-matching techniques to describe and imitate human paths, but often do not generalize well since the feature values can vary from person to person, and even run to run. This work notes that while it is challenging to directly specify the details of what to do (precise mechanisms of human navigation), it is straightforward to specify what not to do (violations of social norms). Specifically, using deep reinforcement learning, this work develops a time-efficient navigation policy that respects common social norms. The proposed method is shown to enable fully autonomous navigation of a robotic vehicle moving at human walking speed in an environment with many pedestrians. |
| Tasks | Autonomous Navigation, Motion Planning |
| Published | 2017-03-26 |
| URL | http://arxiv.org/abs/1703.08862v2 |
| http://arxiv.org/pdf/1703.08862v2.pdf | |
| PWC | https://paperswithcode.com/paper/socially-aware-motion-planning-with-deep |
| Repo | https://github.com/mit-acl/gym-collision-avoidance |
| Framework | none |
Multi-Task Learning for Segmentation of Building Footprints with Deep Neural Networks
| Title | Multi-Task Learning for Segmentation of Building Footprints with Deep Neural Networks |
| Authors | Benjamin Bischke, Patrick Helber, Joachim Folz, Damian Borth, Andreas Dengel |
| Abstract | The increased availability of high resolution satellite imagery allows to sense very detailed structures on the surface of our planet. Access to such information opens up new directions in the analysis of remote sensing imagery. However, at the same time this raises a set of new challenges for existing pixel-based prediction methods, such as semantic segmentation approaches. While deep neural networks have achieved significant advances in the semantic segmentation of high resolution images in the past, most of the existing approaches tend to produce predictions with poor boundaries. In this paper, we address the problem of preserving semantic segmentation boundaries in high resolution satellite imagery by introducing a new cascaded multi-task loss. We evaluate our approach on Inria Aerial Image Labeling Dataset which contains large-scale and high resolution images. Our results show that we are able to outperform state-of-the-art methods by 8.3% without any additional post-processing step. |
| Tasks | Multi-Task Learning, Semantic Segmentation |
| Published | 2017-09-18 |
| URL | http://arxiv.org/abs/1709.05932v1 |
| http://arxiv.org/pdf/1709.05932v1.pdf | |
| PWC | https://paperswithcode.com/paper/multi-task-learning-for-segmentation-of |
| Repo | https://github.com/melissande/dhi-segmentation-buildings |
| Framework | pytorch |
Know Your Master: Driver Profiling-based Anti-theft Method
| Title | Know Your Master: Driver Profiling-based Anti-theft Method |
| Authors | Byung Il Kwak, JiYoung Woo, Huy Kang Kim |
| Abstract | Although many anti-theft technologies are implemented, auto-theft is still increasing. Also, security vulnerabilities of cars can be used for auto-theft by neutralizing anti-theft system. This keyless auto-theft attack will be increased as cars adopt computerized electronic devices more. To detect auto-theft efficiently, we propose the driver verification method that analyzes driving patterns using measurements from the sensor in the vehicle. In our model, we add mechanical features of automotive parts that are excluded in previous works, but can be differentiated by drivers’ driving behaviors. We design the model that uses significant features through feature selection to reduce the time cost of feature processing and improve the detection performance. Further, we enrich the feature set by deriving statistical features such as mean, median, and standard deviation. This minimizes the effect of fluctuation of feature values per driver and finally generates the reliable model. We also analyze the effect of the size of sliding window on performance to detect the time point when the detection becomes reliable and to inform owners the theft event as soon as possible. We apply our model with real driving and show the contribution of our work to the literature of driver identification. |
| Tasks | Feature Selection |
| Published | 2017-04-18 |
| URL | http://arxiv.org/abs/1704.05223v1 |
| http://arxiv.org/pdf/1704.05223v1.pdf | |
| PWC | https://paperswithcode.com/paper/know-your-master-driver-profiling-based-anti |
| Repo | https://github.com/yoshino0705/Driver_Behavior_Recognition |
| Framework | none |
Failing to Learn: Autonomously Identifying Perception Failures for Self-driving Cars
| Title | Failing to Learn: Autonomously Identifying Perception Failures for Self-driving Cars |
| Authors | Manikandasriram Srinivasan Ramanagopal, Cyrus Anderson, Ram Vasudevan, Matthew Johnson-Roberson |
| Abstract | One of the major open challenges in self-driving cars is the ability to detect cars and pedestrians to safely navigate in the world. Deep learning-based object detector approaches have enabled great advances in using camera imagery to detect and classify objects. But for a safety critical application, such as autonomous driving, the error rates of the current state of the art are still too high to enable safe operation. Moreover, the characterization of object detector performance is primarily limited to testing on prerecorded datasets. Errors that occur on novel data go undetected without additional human labels. In this letter, we propose an automated method to identify mistakes made by object detectors without ground truth labels. We show that inconsistencies in the object detector output between a pair of similar images can be used as hypotheses for false negatives (e.g., missed detections) and using a novel set of features for each hypothesis, an off-the-shelf binary classifier can be used to find valid errors. In particular, we study two distinct cues - temporal and stereo inconsistencies - using data that are readily available on most autonomous vehicles. Our method can be used with any camera-based object detector and we illustrate the technique on several sets of real world data. We show that a state-of-the-art detector, tracker, and our classifier trained only on synthetic data can identify valid errors on KITTI tracking dataset with an average precision of 0.94. We also release a new tracking dataset with 104 sequences totaling 80,655 labeled pairs of stereo images along with ground truth disparity from a game engine to facilitate further research. The dataset and code are available at https://fcav.engin.umich.edu/research/failing-to-learn |
| Tasks | Autonomous Driving, Autonomous Vehicles, Object Detection, Self-Driving Cars |
| Published | 2017-06-30 |
| URL | http://arxiv.org/abs/1707.00051v4 |
| http://arxiv.org/pdf/1707.00051v4.pdf | |
| PWC | https://paperswithcode.com/paper/failing-to-learn-autonomously-identifying |
| Repo | https://github.com/umautobots/failing-to-learn |
| Framework | none |
Distributionally Ambiguous Optimization Techniques for Batch Bayesian Optimization
| Title | Distributionally Ambiguous Optimization Techniques for Batch Bayesian Optimization |
| Authors | Nikitas Rontsis, Michael A. Osborne, Paul J. Goulart |
| Abstract | We propose a novel, theoretically-grounded, acquisition function for Batch Bayesian optimization informed by insights from distributionally ambiguous optimization. Our acquisition function is a lower bound on the well-known Expected Improvement function, which requires evaluation of a Gaussian Expectation over a multivariate piecewise affine function. Our bound is computed instead by evaluating the best-case expectation over all probability distributions consistent with the same mean and variance as the original Gaussian distribution. Unlike alternative approaches, including Expected Improvement, our proposed acquisition function avoids multi-dimensional integrations entirely, and can be computed exactly - even on large batch sizes - as the solution of a tractable convex optimization problem. Our suggested acquisition function can also be optimized efficiently, since first and second derivative information can be calculated inexpensively as by-products of the acquisition function calculation itself. We derive various novel theorems that ground our work theoretically and we demonstrate superior performance via simple motivating examples, benchmark functions and real-world problems. |
| Tasks | |
| Published | 2017-07-13 |
| URL | http://arxiv.org/abs/1707.04191v4 |
| http://arxiv.org/pdf/1707.04191v4.pdf | |
| PWC | https://paperswithcode.com/paper/distributionally-ambiguous-optimization |
| Repo | https://github.com/oxfordcontrol/Bayesian-Optimization |
| Framework | tf |
