October 19, 2019

3300 words 16 mins read

Paper Group ANR 287

Deep Learning for End-to-End Automatic Target Recognition from Synthetic Aperture Radar Imagery. A Many-Objective Evolutionary Algorithm Based on Decomposition and Local Dominance. On the Effectiveness of Simple Success-Based Parameter Selection Mechanisms for Two Classical Discrete Black-Box Optimization Benchmark Problems. RGCNN: Regularized Grap …

Deep Learning for End-to-End Automatic Target Recognition from Synthetic Aperture Radar Imagery


Title	Deep Learning for End-to-End Automatic Target Recognition from Synthetic Aperture Radar Imagery
Authors	Hidetoshi Furukawa
Abstract	The standard architecture of synthetic aperture radar (SAR) automatic target recognition (ATR) consists of three stages: detection, discrimination, and classification. In recent years, convolutional neural networks (CNNs) for SAR ATR have been proposed, but most of them classify target classes from a target chip extracted from SAR imagery, as a classification for the third stage of SAR ATR. In this report, we propose a novel CNN for end-to-end ATR from SAR imagery. The CNN named verification support network (VersNet) performs all three stages of SAR ATR end-to-end. VersNet inputs a SAR image of arbitrary sizes with multiple classes and multiple targets, and outputs a SAR ATR image representing the position, class, and pose of each detected target. This report describes the evaluation results of VersNet which trained to output scores of all 12 classes: 10 target classes, a target front class, and a background class, for each pixel using the moving and stationary target acquisition and recognition (MSTAR) public dataset.
Tasks
Published	2018-01-25
URL	http://arxiv.org/abs/1801.08558v1
PDF	http://arxiv.org/pdf/1801.08558v1.pdf
PWC	https://paperswithcode.com/paper/deep-learning-for-end-to-end-automatic-target
Repo
Framework

A Many-Objective Evolutionary Algorithm Based on Decomposition and Local Dominance


Title	A Many-Objective Evolutionary Algorithm Based on Decomposition and Local Dominance
Authors	Yingyu Zhang, Yuanzhen Li, Quan-Ke Panb, P. N. Suganthan
Abstract	Many-objective evolutionary algorithms (MOEAs), especially the decomposition-based MOEAs, have attracted wide attention in recent years. Recent studies show that a well designed combination of the decomposition method and the domination method can improve the performance ,i.e., convergence and diversity, of a MOEA. In this paper, a novel way of combining the decomposition method and the domination method is proposed. More precisely, a set of weight vectors is employed to decompose a given many-objective optimization problem(MaOP), and a hybrid method of the penalty-based boundary intersection function and dominance is proposed to compare local solutions within a subpopulation defined by a weight vector. A MOEA based on the hybrid method is implemented and tested on problems chosen from two famous test suites, i.e., DTLZ and WFG. The experimental results show that our algorithm is very competitive in dealing with MaOPs. Subsequently, our algorithm is extended to solve constraint MaOPs, and the constrained version of our algorithm also shows good performance in terms of convergence and diversity. These reveals that using dominance locally and combining it with the decomposition method can effectively improve the performance of a MOEA.
Tasks
Published	2018-07-13
URL	https://arxiv.org/abs/1807.10275v2
PDF	https://arxiv.org/pdf/1807.10275v2.pdf
PWC	https://paperswithcode.com/paper/a-many-objective-evolutionary-algorithm-based
Repo
Framework

On the Effectiveness of Simple Success-Based Parameter Selection Mechanisms for Two Classical Discrete Black-Box Optimization Benchmark Problems


Title	On the Effectiveness of Simple Success-Based Parameter Selection Mechanisms for Two Classical Discrete Black-Box Optimization Benchmark Problems
Authors	Carola Doerr, Markus Wagner
Abstract	Despite significant empirical and theoretically supported evidence that non-static parameter choices can be strongly beneficial in evolutionary computation, the question how to best adjust parameter values plays only a marginal role in contemporary research on discrete black-box optimization. This has led to the unsatisfactory situation in which feedback-free parameter selection rules such as the cooling schedule of Simulated Annealing are predominant in state-of-the-art heuristics, while, at the same time, we understand very well that such time-dependent selection rules can only perform worse than adjustment rules that do take into account the evolution of the optimization process. A number of adaptive and self-adaptive parameter control strategies have been proposed in the literature, but did not (yet) make their way to a broader public. A key obstacle seems to lie in their rather complex update rules. The purpose of our work is to demonstrate that high-performing online parameter selection rules do not have to be very complicated. More precisely, we experiment with a multiplicative, comparison-based update rule to adjust the mutation probability of a (1+1)~Evolutionary Algorithm. We show that this simple self-adjusting rule outperforms the best static unary unbiased black-box algorithm on LeadingOnes, achieving an almost optimal speedup of about~$18%$.
Tasks
Published	2018-03-04
URL	http://arxiv.org/abs/1803.01425v1
PDF	http://arxiv.org/pdf/1803.01425v1.pdf
PWC	https://paperswithcode.com/paper/on-the-effectiveness-of-simple-success-based
Repo
Framework

RGCNN: Regularized Graph CNN for Point Cloud Segmentation


Title	RGCNN: Regularized Graph CNN for Point Cloud Segmentation
Authors	Gusi Te, Wei Hu, Zongming Guo, Amin Zheng
Abstract	Point cloud, an efficient 3D object representation, has become popular with the development of depth sensing and 3D laser scanning techniques. It has attracted attention in various applications such as 3D tele-presence, navigation for unmanned vehicles and heritage reconstruction. The understanding of point clouds, such as point cloud segmentation, is crucial in exploiting the informative value of point clouds for such applications. Due to the irregularity of the data format, previous deep learning works often convert point clouds to regular 3D voxel grids or collections of images before feeding them into neural networks, which leads to voluminous data and quantization artifacts. In this paper, we instead propose a regularized graph convolutional neural network (RGCNN) that directly consumes point clouds. Leveraging on spectral graph theory, we treat features of points in a point cloud as signals on graph, and define the convolution over graph by Chebyshev polynomial approximation. In particular, we update the graph Laplacian matrix that describes the connectivity of features in each layer according to the corresponding learned features, which adaptively captures the structure of dynamic graphs. Further, we deploy a graph-signal smoothness prior in the loss function, thus regularizing the learning process. Experimental results on the ShapeNet part dataset show that the proposed approach significantly reduces the computational complexity while achieving competitive performance with the state of the art. Also, experiments show RGCNN is much more robust to both noise and point cloud density in comparison with other methods. We further apply RGCNN to point cloud classification and achieve competitive results on ModelNet40 dataset.
Tasks	Quantization
Published	2018-06-08
URL	http://arxiv.org/abs/1806.02952v1
PDF	http://arxiv.org/pdf/1806.02952v1.pdf
PWC	https://paperswithcode.com/paper/rgcnn-regularized-graph-cnn-for-point-cloud
Repo
Framework

Interaction-Aware Probabilistic Behavior Prediction in Urban Environments


Title	Interaction-Aware Probabilistic Behavior Prediction in Urban Environments
Authors	Jens Schulz, Constantin Hubmann, Julian Löchner, Darius Burschka
Abstract	Planning for autonomous driving in complex, urban scenarios requires accurate prediction of the trajectories of surrounding traffic participants. Their future behavior depends on their route intentions, the road-geometry, traffic rules and mutual interaction, resulting in interdependencies between their trajectories. We present a probabilistic prediction framework based on a dynamic Bayesian network, which represents the state of the complete scene including all agents and respects the aforementioned dependencies. We propose Markovian, context-dependent motion models to define the interaction-aware behavior of drivers. At first, the state of the dynamic Bayesian network is estimated over time by tracking the single agents via sequential Monte Carlo inference. Secondly, we perform a probabilistic forward simulation of the network’s estimated belief state to generate the different combinatorial scene developments. This provides the corresponding trajectories for the set of possible, future scenes. Our framework can handle various road layouts and number of traffic participants. We evaluate the approach in online simulations and real-world scenarios. It is shown that our interaction-aware prediction outperforms interaction-unaware physics- and map-based approaches.
Tasks	Autonomous Driving
Published	2018-04-27
URL	http://arxiv.org/abs/1804.10467v2
PDF	http://arxiv.org/pdf/1804.10467v2.pdf
PWC	https://paperswithcode.com/paper/interaction-aware-probabilistic-behavior
Repo
Framework

Long-Term Occupancy Grid Prediction Using Recurrent Neural Networks


Title	Long-Term Occupancy Grid Prediction Using Recurrent Neural Networks
Authors	Marcel Schreiber, Stefan Hoermann, Klaus Dietmayer
Abstract	We tackle the long-term prediction of scene evolution in a complex downtown scenario for automated driving based on Lidar grid fusion and recurrent neural networks (RNNs). A bird’s eye view of the scene, including occupancy and velocity, is fed as a sequence to a RNN which is trained to predict future occupancy. The nature of prediction allows generation of multiple hours of training data without the need of manual labeling. Thus, the training strategy and loss function is designed for long sequences of real-world data (unbalanced, continuously changing situations, false labels, etc.). The deep CNN architecture comprises convolutional long short-term memories (ConvLSTMs) to separate static from dynamic regions and to predict dynamic objects in future frames. Novel recurrent skip connections show the ability to predict small occluded objects, i.e. pedestrians, and occluded static regions. Spatio-temporal correlations between grid cells are exploited to predict multimodal future paths and interactions between objects. Experiments also quantify improvements to our previous network, a Monte Carlo approach, and literature.
Tasks
Published	2018-09-11
URL	https://arxiv.org/abs/1809.03782v2
PDF	https://arxiv.org/pdf/1809.03782v2.pdf
PWC	https://paperswithcode.com/paper/long-term-occupancy-grid-prediction-using
Repo
Framework

Classifying Process Instances Using Recurrent Neural Networks


Title	Classifying Process Instances Using Recurrent Neural Networks
Authors	Markku Hinkka, Teemu Lehto, Keijo Heljanko, Alexander Jung
Abstract	Process Mining consists of techniques where logs created by operative systems are transformed into process models. In process mining tools it is often desired to be able to classify ongoing process instances, e.g., to predict how long the process will still require to complete, or to classify process instances to different classes based only on the activities that have occurred in the process instance thus far. Recurrent neural networks and its subclasses, such as Gated Recurrent Unit (GRU) and Long Short-Term Memory (LSTM), have been demonstrated to be able to learn relevant temporal features for subsequent classification tasks. In this paper we apply recurrent neural networks to classifying process instances. The proposed model is trained in a supervised fashion using labeled process instances extracted from event log traces. This is the first time we know of GRU having been used in classifying business process instances. Our main experimental results shows that GRU outperforms LSTM remarkably in training time while giving almost identical accuracies to LSTM models. Additional contributions of our paper are improving the classification model training time by filtering infrequent activities, which is a technique commonly used, e.g., in Natural Language Processing (NLP).
Tasks
Published	2018-09-16
URL	http://arxiv.org/abs/1809.05896v1
PDF	http://arxiv.org/pdf/1809.05896v1.pdf
PWC	https://paperswithcode.com/paper/classifying-process-instances-using-recurrent
Repo
Framework

Discovering User Groups for Natural Language Generation


Title	Discovering User Groups for Natural Language Generation
Authors	Nikos Engonopoulos, Christoph Teichmann, Alexander Koller
Abstract	We present a model which predicts how individual users of a dialog system understand and produce utterances based on user groups. In contrast to previous work, these user groups are not specified beforehand, but learned in training. We evaluate on two referring expression (RE) generation tasks; our experiments show that our model can identify user groups and learn how to most effectively talk to them, and can dynamically assign unseen users to the correct groups as they interact with the system.
Tasks	Text Generation
Published	2018-06-15
URL	http://arxiv.org/abs/1806.05947v1
PDF	http://arxiv.org/pdf/1806.05947v1.pdf
PWC	https://paperswithcode.com/paper/discovering-user-groups-for-natural-language
Repo
Framework

Variational Knowledge Graph Reasoning


Title	Variational Knowledge Graph Reasoning
Authors	Wenhu Chen, Wenhan Xiong, Xifeng Yan, William Wang
Abstract	Inferring missing links in knowledge graphs (KG) has attracted a lot of attention from the research community. In this paper, we tackle a practical query answering task involving predicting the relation of a given entity pair. We frame this prediction problem as an inference problem in a probabilistic graphical model and aim at resolving it from a variational inference perspective. In order to model the relation between the query entity pair, we assume that there exists an underlying latent variable (paths connecting two nodes) in the KG, which carries the equivalent semantics of their relations. However, due to the intractability of connections in large KGs, we propose to use variation inference to maximize the evidence lower bound. More specifically, our framework (\textsc{Diva}) is composed of three modules, i.e. a posterior approximator, a prior (path finder), and a likelihood (path reasoner). By using variational inference, we are able to incorporate them closely into a unified architecture and jointly optimize them to perform KG reasoning. With active interactions among these sub-modules, \textsc{Diva} is better at handling noise and coping with more complex reasoning scenarios. In order to evaluate our method, we conduct the experiment of the link prediction task on multiple datasets and achieve state-of-the-art performances on both datasets.
Tasks	Knowledge Graphs, Link Prediction
Published	2018-03-17
URL	http://arxiv.org/abs/1803.06581v3
PDF	http://arxiv.org/pdf/1803.06581v3.pdf
PWC	https://paperswithcode.com/paper/variational-knowledge-graph-reasoning
Repo
Framework

Multi-Source Syntactic Neural Machine Translation


Title	Multi-Source Syntactic Neural Machine Translation
Authors	Anna Currey, Kenneth Heafield
Abstract	We introduce a novel multi-source technique for incorporating source syntax into neural machine translation using linearized parses. This is achieved by employing separate encoders for the sequential and parsed versions of the same source sentence; the resulting representations are then combined using a hierarchical attention mechanism. The proposed model improves over both seq2seq and parsed baselines by over 1 BLEU on the WMT17 English-German task. Further analysis shows that our multi-source syntactic model is able to translate successfully without any parsed input, unlike standard parsed methods. In addition, performance does not deteriorate as much on long sentences as for the baselines.
Tasks	Machine Translation
Published	2018-08-30
URL	http://arxiv.org/abs/1808.10267v1
PDF	http://arxiv.org/pdf/1808.10267v1.pdf
PWC	https://paperswithcode.com/paper/multi-source-syntactic-neural-machine
Repo
Framework

Text Embeddings for Retrieval From a Large Knowledge Base


Title	Text Embeddings for Retrieval From a Large Knowledge Base
Authors	Tolgahan Cakaloglu, Christian Szegedy, Xiaowei Xu
Abstract	Text embedding representing natural language documents in a semantic vector space can be used for document retrieval using nearest neighbor lookup. In order to study the feasibility of neural models specialized for retrieval in a semantically meaningful way, we suggest the use of the Stanford Question Answering Dataset (SQuAD) in an open-domain question answering context, where the first task is to find paragraphs useful for answering a given question. First, we compare the quality of various text-embedding methods on the performance of retrieval and give an extensive empirical comparison on the performance of various non-augmented base embedding with, and without IDF weighting. Our main results are that by training deep residual neural models, specifically for retrieval purposes, can yield significant gains when it is used to augment existing embeddings. We also establish that deeper models are superior to this task. The best base baseline embeddings augmented by our learned neural approach improves the top-1 paragraph recall of the system by 14%.
Tasks	Open-Domain Question Answering, Question Answering
Published	2018-10-24
URL	https://arxiv.org/abs/1810.10176v2
PDF	https://arxiv.org/pdf/1810.10176v2.pdf
PWC	https://paperswithcode.com/paper/text-embeddings-for-retrieval-from-a-large
Repo
Framework

Path to Stochastic Stability: Comparative Analysis of Stochastic Learning Dynamics in Games


Title	Path to Stochastic Stability: Comparative Analysis of Stochastic Learning Dynamics in Games
Authors	Hassan Jaleel, Jeff S. Shamma
Abstract	Stochastic stability is a popular solution concept for stochastic learning dynamics in games. However, a critical limitation of this solution concept is its inability to distinguish between different learning rules that lead to the same steady-state behavior. We address this limitation for the first time and develop a framework for the comparative analysis of stochastic learning dynamics with different update rules but same steady-state behavior. We present the framework in the context of two learning dynamics: Log-Linear Learning (LLL) and Metropolis Learning (ML). Although both of these dynamics have the same stochastically stable states, LLL and ML correspond to different behavioral models for decision making. Moreover, we demonstrate through an example setup of sensor coverage game that for each of these dynamics, the paths to stochastically stable states exhibit distinctive behaviors. Therefore, we propose multiple criteria to analyze and quantify the differences in the short and medium run behavior of stochastic learning dynamics. We derive and compare upper bounds on the expected hitting time to the set of Nash equilibria for both LLL and ML. For the medium to long-run behavior, we identify a set of tools from the theory of perturbed Markov chains that result in a hierarchical decomposition of the state space into collections of states called cycles. We compare LLL and ML based on the proposed criteria and develop invaluable insights into the comparative behavior of the two dynamics.
Tasks	Decision Making
Published	2018-04-08
URL	http://arxiv.org/abs/1804.02693v1
PDF	http://arxiv.org/pdf/1804.02693v1.pdf
PWC	https://paperswithcode.com/paper/path-to-stochastic-stability-comparative
Repo
Framework

Learning Models for Shared Control of Human-Machine Systems with Unknown Dynamics


Title	Learning Models for Shared Control of Human-Machine Systems with Unknown Dynamics
Authors	Alexander Broad, Todd Murphey, Brenna Argall
Abstract	We present a novel approach to shared control of human-machine systems. Our method assumes no a priori knowledge of the system dynamics. Instead, we learn both the dynamics and information about the user’s interaction from observation through the use of the Koopman operator. Using the learned model, we define an optimization problem to compute the optimal policy for a given task, and compare the user input to the optimal input. We demonstrate the efficacy of our approach with a user study. We also analyze the individual nature of the learned models by comparing the effectiveness of our approach when the demonstration data comes from a user’s own interactions, from the interactions of a group of users and from a domain expert. Positive results include statistically significant improvements on task metrics when comparing a user-only control paradigm with our shared control paradigm. Surprising results include findings that suggest that individualizing the model based on a user’s own data does not effect the ability to learn a useful dynamic system. We explore this tension as it relates to developing human-in-the-loop systems further in the discussion.
Tasks
Published	2018-08-24
URL	http://arxiv.org/abs/1808.08268v1
PDF	http://arxiv.org/pdf/1808.08268v1.pdf
PWC	https://paperswithcode.com/paper/learning-models-for-shared-control-of-human
Repo
Framework

Learning to Communicate: A Machine Learning Framework for Heterogeneous Multi-Agent Robotic Systems


Title	Learning to Communicate: A Machine Learning Framework for Heterogeneous Multi-Agent Robotic Systems
Authors	Hyung-Jin Yoon, Huaiyu Chen, Kehan Long, Heling Zhang, Aditya Gahlawat, Donghwan Lee, Naira Hovakimyan
Abstract	We present a machine learning framework for multi-agent systems to learn both the optimal policy for maximizing the rewards and the encoding of the high dimensional visual observation. The encoding is useful for sharing local visual observations with other agents under communication resource constraints. The actor-encoder encodes the raw images and chooses an action based on local observations and messages sent by the other agents. The machine learning agent generates not only an actuator command to the physical device, but also a communication message to the other agents. We formulate a reinforcement learning problem, which extends the action space to consider the communication action as well. The feasibility of the reinforcement learning framework is demonstrated using a 3D simulation environment with two collaborating agents. The environment provides realistic visual observations to be used and shared between the two agents.
Tasks
Published	2018-12-13
URL	http://arxiv.org/abs/1812.05256v1
PDF	http://arxiv.org/pdf/1812.05256v1.pdf
PWC	https://paperswithcode.com/paper/learning-to-communicate-a-machine-learning
Repo
Framework

Testing Matrix Rank, Optimally


Title	Testing Matrix Rank, Optimally
Authors	Maria-Florina Balcan, Yi Li, David P. Woodruff, Hongyang Zhang
Abstract	We show that for the problem of testing if a matrix $A \in F^{n \times n}$ has rank at most $d$, or requires changing an $\epsilon$-fraction of entries to have rank at most $d$, there is a non-adaptive query algorithm making $\widetilde{O}(d^2/\epsilon)$ queries. Our algorithm works for any field $F$. This improves upon the previous $O(d^2/\epsilon^2)$ bound (SODA’03), and bypasses an $\Omega(d^2/\epsilon^2)$ lower bound of (KDD’14) which holds if the algorithm is required to read a submatrix. Our algorithm is the first such algorithm which does not read a submatrix, and instead reads a carefully selected non-adaptive pattern of entries in rows and columns of $A$. We complement our algorithm with a matching query complexity lower bound for non-adaptive testers over any field. We also give tight bounds of $\widetilde{\Theta}(d^2)$ queries in the sensing model for which query access comes in the form of $\langle X_i, A\rangle:=tr(X_i^\top A)$; perhaps surprisingly these bounds do not depend on $\epsilon$. We next develop a novel property testing framework for testing numerical properties of a real-valued matrix $A$ more generally, which includes the stable rank, Schatten-$p$ norms, and SVD entropy. Specifically, we propose a bounded entry model, where $A$ is required to have entries bounded by $1$ in absolute value. We give upper and lower bounds for a wide range of problems in this model, and discuss connections to the sensing model above.
Tasks
Published	2018-10-18
URL	http://arxiv.org/abs/1810.08171v1
PDF	http://arxiv.org/pdf/1810.08171v1.pdf
PWC	https://paperswithcode.com/paper/testing-matrix-rank-optimally
Repo
Framework