January 28, 2020

3210 words 16 mins read

Paper Group ANR 955

Pixel-Wise PolSAR Image Classification via a Novel Complex-Valued Deep Fully Convolutional Network. What’s in my Room? Object Recognition on Indoor Panoramic Images. Brain-Inspired Inference on Missing Video Sequence. Improving a State-of-the-Art Heuristic for the Minimum Latency Problem with Data Mining. Large-scale text processing pipeline with A …

Pixel-Wise PolSAR Image Classification via a Novel Complex-Valued Deep Fully Convolutional Network


Title	Pixel-Wise PolSAR Image Classification via a Novel Complex-Valued Deep Fully Convolutional Network
Authors	Yice Cao, Yan Wu, Peng Zhang, Wenkai Liang, Ming Li
Abstract	Although complex-valued (CV) neural networks have shown better classification results compared to their real-valued (RV) counterparts for polarimetric synthetic aperture radar (PolSAR) classification, the extension of pixel-level RV networks to the complex domain has not yet thoroughly examined. This paper presents a novel complex-valued deep fully convolutional neural network (CV-FCN) designed for PolSAR image classification. Specifically, CV-FCN uses PolSAR CV data that includes the phase information and utilizes the deep FCN architecture that performs pixel-level labeling. It integrates the feature extraction module and the classification module in a united framework. Technically, for the particularity of PolSAR data, a dedicated complex-valued weight initialization scheme is defined to initialize CV-FCN. It considers the distribution of polarization data to conduct CV-FCN training from scratch in an efficient and fast manner. CV-FCN employs a complex downsampling-then-upsampling scheme to extract dense features. To enrich discriminative information, multi-level CV features that retain more polarization information are extracted via the complex downsampling scheme. Then, a complex upsampling scheme is proposed to predict dense CV labeling. It employs complex max-unpooling layers to greatly capture more spatial information for better robustness to speckle noise. In addition, to achieve faster convergence and obtain more precise classification results, a novel average cross-entropy loss function is derived for CV-FCN optimization. Experiments on real PolSAR datasets demonstrate that CV-FCN achieves better classification performance than other state-of-art methods.
Tasks	Image Classification
Published	2019-09-29
URL	https://arxiv.org/abs/1909.13299v1
PDF	https://arxiv.org/pdf/1909.13299v1.pdf
PWC	https://paperswithcode.com/paper/pixel-wise-polsar-image-classification-via-a
Repo
Framework

What’s in my Room? Object Recognition on Indoor Panoramic Images


Title	What’s in my Room? Object Recognition on Indoor Panoramic Images
Authors	Julia Guerrero-Viu, Clara Fernandez-Labrador, Cédric Demonceaux, Jose J. Guerrero
Abstract	In the last few years, there has been a growing interest in taking advantage of the 360 panoramic images potential, while managing the new challenges they imply. While several tasks have been improved thanks to the contextual information these images offer, object recognition in indoor scenes still remains a challenging problem that has not been deeply investigated. This paper provides an object recognition system that performs object detection and semantic segmentation tasks by using a deep learning model adapted to match the nature of equirectangular images. From these results, instance segmentation masks are recovered, refined and transformed into 3D bounding boxes that are placed into the 3D model of the room. Quantitative and qualitative results support that our method outperforms the state of the art by a large margin and show a complete understanding of the main objects in indoor scenes.
Tasks	Instance Segmentation, Object Detection, Object Recognition, Semantic Segmentation
Published	2019-10-14
URL	https://arxiv.org/abs/1910.06138v1
PDF	https://arxiv.org/pdf/1910.06138v1.pdf
PWC	https://paperswithcode.com/paper/whats-in-my-room-object-recognition-on-indoor
Repo
Framework

Brain-Inspired Inference on Missing Video Sequence


Title	Brain-Inspired Inference on Missing Video Sequence
Authors	Weimian Li, Baoyang Chen, Wenmin Wang
Abstract	In this paper, we propose a novel end-to-end architecture that could generate a variety of plausible video sequences correlating two given discontinuous frames. Our work is inspired by the human ability of inference. Specifically, given two static images, human are capable of inferring what might happen in between as well as present diverse versions of their inference. We firstly train our model to learn the transformation to understand the movement trends within given frames. For the sake of imitating the inference of human, we introduce a latent variable sampled from Gaussian distribution. By means of integrating different latent variables with learned transformation features, the model could learn more various possible motion modes. Then applying these motion modes on the original frame, we could acquire various corresponding intermediate video sequence. Moreover, the framework is trained in adversarial fashion with unsupervised learning. Evaluating on the moving Mnist dataset and the 2D Shapes dataset, we show that our model is capable of imitating the human inference to some extent.
Tasks
Published	2019-12-15
URL	https://arxiv.org/abs/1912.06980v1
PDF	https://arxiv.org/pdf/1912.06980v1.pdf
PWC	https://paperswithcode.com/paper/brain-inspired-inference-on-missing-video
Repo
Framework

Improving a State-of-the-Art Heuristic for the Minimum Latency Problem with Data Mining


Title	Improving a State-of-the-Art Heuristic for the Minimum Latency Problem with Data Mining
Authors	Ítalo Gomes Santana
Abstract	Recently, hybrid metaheuristics have become a trend in operations research. A successful example combines the Greedy Randomized Adaptive Search Procedures (GRASP) and data mining techniques, where frequent patterns found in high-quality solutions can lead to an efficient exploration of the search space, along with a significant reduction of computational time. In this work, a GRASP-based state-of-the-art heuristic for the Minimum Latency Problem (MLP) is improved by means of data mining techniques for two MLP variants. Computational experiments showed that the approaches with data mining were able to match or improve the solution quality for a large number of instances, together with a substantial reduction of running time. In addition, 88 new cost values of solutions are introduced into the literature. To support our results, tests of statistical significance, impact of using mined patterns, equal time comparisons and time-to-target plots are provided.
Tasks	Efficient Exploration
Published	2019-08-28
URL	https://arxiv.org/abs/1908.10705v1
PDF	https://arxiv.org/pdf/1908.10705v1.pdf
PWC	https://paperswithcode.com/paper/improving-a-state-of-the-art-heuristic-for
Repo
Framework

Large-scale text processing pipeline with Apache Spark


Title	Large-scale text processing pipeline with Apache Spark
Authors	Alexey Svyatkovskiy, Kosuke Imai, Mary Kroeger, Yuki Shiraito
Abstract	In this paper, we evaluate Apache Spark for a data-intensive machine learning problem. Our use case focuses on policy diffusion detection across the state legislatures in the United States over time. Previous work on policy diffusion has been unable to make an all-pairs comparison between bills due to computational intensity. As a substitute, scholars have studied single topic areas. We provide an implementation of this analysis workflow as a distributed text processing pipeline with Spark dataframes and Scala application programming interface. We discuss the challenges and strategies of unstructured data processing, data formats for storage and efficient access, and graph processing at scale.
Tasks
Published	2019-12-02
URL	https://arxiv.org/abs/1912.00547v1
PDF	https://arxiv.org/pdf/1912.00547v1.pdf
PWC	https://paperswithcode.com/paper/large-scale-text-processing-pipeline-with
Repo
Framework

Fast-UAP: An Algorithm for Speeding up Universal Adversarial Perturbation Generation with Orientation of Perturbation Vectors


Title	Fast-UAP: An Algorithm for Speeding up Universal Adversarial Perturbation Generation with Orientation of Perturbation Vectors
Authors	Jiazhu Dai, Le Shu
Abstract	Convolutional neural networks (CNN) have become one of the most popular machine learning tools and are being applied in various tasks, however, CNN models are vulnerable to universal perturbations, which are usually human-imperceptible but can cause natural images to be misclassified with high probability. One of the state-of-the-art algorithms to generate universal perturbations is known as UAP. UAP only aggregates the minimal perturbations in every iteration, which will lead to generated universal perturbation whose magnitude cannot rise up efficiently and cause a slow generation. In this paper, we proposed an optimized algorithm to improve the performance of crafting universal perturbations based on orientation of perturbation vectors. At each iteration, instead of choosing minimal perturbation vector with respect to each image, we aggregate the current instance of universal perturbation with the perturbation which has similar orientation to the former so that the magnitude of the aggregation will rise up as large as possible at every iteration. The experiment results show that we get universal perturbations in a shorter time and with a smaller number of training images. Furthermore, we observe in experiments that universal perturbations generated by our proposed algorithm have an average increment of fooling rate by 9% in white-box attacks and black-box attacks comparing with universal perturbations generated by UAP.
Tasks
Published	2019-11-04
URL	https://arxiv.org/abs/1911.01172v3
PDF	https://arxiv.org/pdf/1911.01172v3.pdf
PWC	https://paperswithcode.com/paper/fast-uap-algorithm-for-speeding-up-universal
Repo
Framework

Eliminating cross-camera bias for vehicle re-identification


Title	Eliminating cross-camera bias for vehicle re-identification
Authors	Jinjia Peng, Guangqi Jiang, Dongyan Chen, Tongtong Zhao, Huibing Wang, Xianping Fu
Abstract	Vehicle re-identification (reID) often requires recognize a target vehicle in large datasets captured from multi-cameras. It plays an important role in the automatic analysis of the increasing urban surveillance videos, which has become a hot topic in recent years. However, the appearance of vehicle images is easily affected by the environment that various illuminations, different backgrounds and viewpoints, which leads to the large bias between different cameras. To address this problem, this paper proposes a cross-camera adaptation framework (CCA), which smooths the bias by exploiting the common space between cameras for all samples. CCA first transfers images from multi-cameras into one camera to reduce the impact of the illumination and resolution, which generates the samples with the similar distribution. Then, to eliminate the influence of background and focus on the valuable parts, we propose an attention alignment network (AANet) to learn powerful features for vehicle reID. Specially, in AANet, the spatial transfer network with attention module is introduced to locate a series of the most discriminative regions with high-attention weights and suppress the background. Moreover, comprehensive experimental results have demonstrated that our proposed CCA can achieve excellent performances on benchmark datasets VehicleID and VeRi-776.
Tasks	Vehicle Re-Identification
Published	2019-12-21
URL	https://arxiv.org/abs/1912.10193v1
PDF	https://arxiv.org/pdf/1912.10193v1.pdf
PWC	https://paperswithcode.com/paper/eliminating-cross-camera-bias-for-vehicle-re
Repo
Framework

Cooperative Lane Changing via Deep Reinforcement Learning


Title	Cooperative Lane Changing via Deep Reinforcement Learning
Authors	Guan Wang, Jianming Hu, Zhiheng Li, Li Li
Abstract	In this paper, we study how to learn an appropriate lane changing strategy for autonomous vehicles by using deep reinforcement learning. We show that the reward of the system should consider the overall traffic efficiency instead of the travel efficiency of an individual vehicle. In summary, cooperation leads to a more harmonic and efficient traffic system rather than competition
Tasks	Autonomous Vehicles
Published	2019-06-20
URL	https://arxiv.org/abs/1906.08662v1
PDF	https://arxiv.org/pdf/1906.08662v1.pdf
PWC	https://paperswithcode.com/paper/cooperative-lane-changing-via-deep
Repo
Framework

A Transfer Learning Approach for Network Intrusion Detection


Title	A Transfer Learning Approach for Network Intrusion Detection
Authors	Peilun Wu, Hui Guo, Richard Buckland
Abstract	Convolution Neural Network (ConvNet) offers a high potential to generalize input data. It has been widely used in many application areas, such as visual imagery, where comprehensive learning datasets are available and a ConvNet model can be well trained and perform the required function effectively. ConvNet can also be applied to network intrusion detection. However, the currently available datasets related to the network intrusion are often inadequate, which makes the ConvNet learning deficient, hence the trained model is not competent in detecting unknown intrusions. In this paper, we propose a ConvNet model using transfer learning for network intrusion detection. The model consists of two concatenated ConvNets and is built on a two-stage learning process: learning a base dataset and transferring the learned knowledge to the learning of the target dataset. Our experiments on the NSL-KDD dataset show that the proposed model can improve the detection accuracy not only on the test dataset containing mostly known attacks (KDDTest+) but also on the test dataset featuring many novel attacks (KDDTest-21) – about 2.68% improvement on KDDTest+ and 22.02% on KDDTest-21 can be achieved, as compared to the traditional ConvNet model.
Tasks	Intrusion Detection, Network Intrusion Detection, Transfer Learning
Published	2019-09-05
URL	https://arxiv.org/abs/1909.02352v4
PDF	https://arxiv.org/pdf/1909.02352v4.pdf
PWC	https://paperswithcode.com/paper/a-transfer-learning-approach-for-network
Repo
Framework

Learning Similarity Conditions Without Explicit Supervision


Title	Learning Similarity Conditions Without Explicit Supervision
Authors	Reuben Tan, Mariya I. Vasileva, Kate Saenko, Bryan A. Plummer
Abstract	Many real-world tasks require models to compare images along multiple similarity conditions (e.g. similarity in color, category or shape). Existing methods often reason about these complex similarity relationships by learning condition-aware embeddings. While such embeddings aid models in learning different notions of similarity, they also limit their capability to generalize to unseen categories since they require explicit labels at test time. To address this deficiency, we propose an approach that jointly learns representations for the different similarity conditions and their contributions as a latent variable without explicit supervision. Comprehensive experiments across three datasets, Polyvore-Outfits, Maryland-Polyvore and UT-Zappos50k, demonstrate the effectiveness of our approach: our model outperforms the state-of-the-art methods, even those that are strongly supervised with pre-defined similarity conditions, on fill-in-the-blank, outfit compatibility prediction and triplet prediction tasks. Finally, we show that our model learns different visually-relevant semantic sub-spaces that allow it to generalize well to unseen categories.
Tasks
Published	2019-08-22
URL	https://arxiv.org/abs/1908.08589v1
PDF	https://arxiv.org/pdf/1908.08589v1.pdf
PWC	https://paperswithcode.com/paper/learning-similarity-conditions-without
Repo
Framework

Neural networks and kernel ridge regression for excited states dynamics of CH$_2$NH$_2^+$: From single-state to multi-state representations and multi-property machine learning models


Title	Neural networks and kernel ridge regression for excited states dynamics of CH$_2$NH$_2^+$: From single-state to multi-state representations and multi-property machine learning models
Authors	Julia Westermayr, Felix A. Faber, Anders S. Christensen, O. Anatole von Lilienfeld, Philipp Marquetand
Abstract	Excited-state dynamics simulations are a powerful tool to investigate photo-induced reactions of molecules and materials and provide complementary information to experiments. Since the applicability of these simulation techniques is limited by the costs of the underlying electronic structure calculations, we develop and assess different machine learning models for this task. The machine learning models are trained on {\emph ab initio} calculations for excited electronic states, using the methylenimmonium cation (CH$_2$NH$_2^+$) as a model system. For the prediction of excited-state properties, multiple outputs are desirable, which is straightforward with neural networks but less explored with kernel ridge regression. We overcome this challenge for kernel ridge regression in the case of energy predictions by encoding the electronic states explicitly in the inputs, in addition to the molecular representation. We adopt this strategy also for our neural networks for comparison. Such a state encoding enables not only kernel ridge regression with multiple outputs but leads also to more accurate machine learning models for state-specific properties. An important goal for excited-state machine learning models is their use in dynamics simulations, which needs not only state-specific information but also couplings, i.e., properties involving pairs of states. Accordingly, we investigate the performance of different models for such coupling elements. Furthermore, we explore how combining all properties in a single neural network affects the accuracy. As an ultimate test for our machine learning models, we carry out excited-state dynamics simulations based on the predicted energies, forces and couplings and, thus, show the scopes and possibilities of machine learning for the treatment of electronically excited states.
Tasks
Published	2019-12-18
URL	https://arxiv.org/abs/1912.08484v1
PDF	https://arxiv.org/pdf/1912.08484v1.pdf
PWC	https://paperswithcode.com/paper/neural-networks-and-kernel-ridge-regression
Repo
Framework

MLAT: Metric Learning for kNN in Streaming Time Series


Title	MLAT: Metric Learning for kNN in Streaming Time Series
Authors	Dongmin Park, Susik Yoon, Hwanjun Song, Jae-Gil Lee
Abstract	Learning a good distance measure for distance-based classification in time series leads to significant performance improvement in many tasks. Specifically, it is critical to effectively deal with variations and temporal dependencies in time series. However, existing metric learning approaches focus on tackling variations mainly using a strict alignment of two sequences, thereby being not able to capture temporal dependencies. To overcome this limitation, we propose MLAT, which covers both alignment and temporal dependencies at the same time. MLAT achieves the alignment effect as well as preserves temporal dependencies by augmenting a given time series using a sliding window. Furthermore, MLAT employs time-invariant metric learning to derive the most appropriate distance measure from the augmented samples which can also capture the temporal dependencies among them well. We show that MLAT outperforms other existing algorithms in the extensive experiments on various real-world data sets.
Tasks	Metric Learning, Time Series
Published	2019-10-23
URL	https://arxiv.org/abs/1910.10368v1
PDF	https://arxiv.org/pdf/1910.10368v1.pdf
PWC	https://paperswithcode.com/paper/mlat-metric-learning-for-knn-in-streaming
Repo
Framework

Entity Personalized Talent Search Models with Tree Interaction Features


Title	Entity Personalized Talent Search Models with Tree Interaction Features
Authors	Cagri Ozcaglar, Sahin Geyik, Brian Schmitz, Prakhar Sharma, Alex Shelkovnykov, Yiming Ma, Erik Buchanan
Abstract	Talent Search systems aim to recommend potential candidates who are a good match to the hiring needs of a recruiter expressed in terms of the recruiter’s search query or job posting. Past work in this domain has focused on linear and nonlinear models which lack preference personalization in the user-level due to being trained only with globally collected recruiter activity data. In this paper, we propose an entity-personalized Talent Search model which utilizes a combination of generalized linear mixed (GLMix) models and gradient boosted decision tree (GBDT) models, and provides personalized talent recommendations using nonlinear tree interaction features generated by the GBDT. We also present the offline and online system architecture for the productionization of this hybrid model approach in our Talent Search systems. Finally, we provide offline and online experiment results benchmarking our entity-personalized model with tree interaction features, which demonstrate significant improvements in our precision metrics compared to globally trained non-personalized models.
Tasks
Published	2019-02-25
URL	http://arxiv.org/abs/1902.09041v1
PDF	http://arxiv.org/pdf/1902.09041v1.pdf
PWC	https://paperswithcode.com/paper/entity-personalized-talent-search-models-with
Repo
Framework

Textured Neural Avatars


Title	Textured Neural Avatars
Authors	Aliaksandra Shysheya, Egor Zakharov, Kara-Ali Aliev, Renat Bashirov, Egor Burkov, Karim Iskakov, Aleksei Ivakhnenko, Yury Malkov, Igor Pasechnik, Dmitry Ulyanov, Alexander Vakhitov, Victor Lempitsky
Abstract	We present a system for learning full-body neural avatars, i.e. deep networks that produce full-body renderings of a person for varying body pose and camera position. Our system takes the middle path between the classical graphics pipeline and the recent deep learning approaches that generate images of humans using image-to-image translation. In particular, our system estimates an explicit two-dimensional texture map of the model surface. At the same time, it abstains from explicit shape modeling in 3D. Instead, at test time, the system uses a fully-convolutional network to directly map the configuration of body feature points w.r.t. the camera to the 2D texture coordinates of individual pixels in the image frame. We show that such a system is capable of learning to generate realistic renderings while being trained on videos annotated with 3D poses and foreground masks. We also demonstrate that maintaining an explicit texture representation helps our system to achieve better generalization compared to systems that use direct image-to-image translation.
Tasks	Image-to-Image Translation
Published	2019-05-21
URL	https://arxiv.org/abs/1905.08776v1
PDF	https://arxiv.org/pdf/1905.08776v1.pdf
PWC	https://paperswithcode.com/paper/textured-neural-avatars-1
Repo
Framework

Spectrum-Diverse Neuroevolution with Unified Neural Models


Title	Spectrum-Diverse Neuroevolution with Unified Neural Models
Authors	Danilo Vasconcellos Vargas, Junichi Murata
Abstract	Learning algorithms are being increasingly adopted in various applications. However, further expansion will require methods that work more automatically. To enable this level of automation, a more powerful solution representation is needed. However, by increasing the representation complexity a second problem arises. The search space becomes huge and therefore an associated scalable and efficient searching algorithm is also required. To solve both problems, first a powerful representation is proposed that unifies most of the neural networks features from the literature into one representation. Secondly, a new diversity preserving method called Spectrum Diversity is created based on the new concept of chromosome spectrum that creates a spectrum out of the characteristics and frequency of alleles in a chromosome. The combination of Spectrum Diversity with a unified neuron representation enables the algorithm to either surpass or equal NeuroEvolution of Augmenting Topologies (NEAT) on all of the five classes of problems tested. Ablation tests justifies the good results, showing the importance of added new features in the unified neuron representation. Part of the success is attributed to the novelty-focused evolution and good scalability with chromosome size provided by Spectrum Diversity. Thus, this study sheds light on a new representation and diversity preserving mechanism that should impact algorithms and applications to come. To download the code please access the following https://github.com/zweifel/Physis-Shard.
Tasks
Published	2019-01-06
URL	http://arxiv.org/abs/1902.06703v1
PDF	http://arxiv.org/pdf/1902.06703v1.pdf
PWC	https://paperswithcode.com/paper/spectrum-diverse-neuroevolution-with-unified
Repo
Framework