October 20, 2019

3202 words 16 mins read

Paper Group ANR 76

Computer-aided mechanism design: designing revenue-optimal mechanisms via neural networks. Visual Semantic Navigation using Scene Priors. Efficient Multi-Robot Coverage of a Known Environment. Correlation Heuristics for Constraint Programming. DEFRAG: Deep Euclidean Feature Representations through Adaptation on the Grassmann Manifold. Knowledge Com …

Computer-aided mechanism design: designing revenue-optimal mechanisms via neural networks


Title	Computer-aided mechanism design: designing revenue-optimal mechanisms via neural networks
Authors	Weiran Shen, Pingzhong Tang, Song Zuo
Abstract	Using AI approaches to automatically design mechanisms has been a central research mission at the interface of AI and economics [Conitzer and Sandholm, 2002]. Previous approaches that a empt to design revenue optimal auctions for the multi-dimensional settings fall short in at least one of the three aspects: 1) representation — search in a space that probably does not even contain the optimal mechanism; 2) exactness — finding a mechanism that is either not truthful or far from optimal; 3) domain dependence — need a different design for different environment settings. To resolve the three difficulties, in this paper, we put forward a uni ed neural network based framework that automatically learns to design revenue optimal mechanisms. Our framework consists of a mechanism network that takes an input distribution for training and outputs a mechanism, as well as a buyer network that takes a mechanism as input and output an action. Such a separation in design mitigates the difficulty to impose incentive compatibility constraints on the mechanism, by making it a rational choice of the buyer. As a result, our framework easily overcomes the previously mentioned difficulty in incorporating IC constraints and always returns exactly incentive compatible mechanisms. We then applied our framework to a number of multi-item revenue optimal design settings, for a few of which the theoretically optimal mechanisms are unknown. We then go on to theoretically prove that the mechanisms found by our framework are indeed optimal.
Tasks
Published	2018-05-09
URL	http://arxiv.org/abs/1805.03382v1
PDF	http://arxiv.org/pdf/1805.03382v1.pdf
PWC	https://paperswithcode.com/paper/computer-aided-mechanism-design-designing
Repo
Framework


Title	Visual Semantic Navigation using Scene Priors
Authors	Wei Yang, Xiaolong Wang, Ali Farhadi, Abhinav Gupta, Roozbeh Mottaghi
Abstract	How do humans navigate to target objects in novel scenes? Do we use the semantic/functional priors we have built over years to efficiently search and navigate? For example, to search for mugs, we search cabinets near the coffee machine and for fruits we try the fridge. In this work, we focus on incorporating semantic priors in the task of semantic navigation. We propose to use Graph Convolutional Networks for incorporating the prior knowledge into a deep reinforcement learning framework. The agent uses the features from the knowledge graph to predict the actions. For evaluation, we use the AI2-THOR framework. Our experiments show how semantic knowledge improves performance significantly. More importantly, we show improvement in generalization to unseen scenes and/or objects. The supplementary video can be accessed at the following link: https://youtu.be/otKjuO805dE .
Tasks
Published	2018-10-15
URL	http://arxiv.org/abs/1810.06543v1
PDF	http://arxiv.org/pdf/1810.06543v1.pdf
PWC	https://paperswithcode.com/paper/visual-semantic-navigation-using-scene-priors
Repo
Framework

Efficient Multi-Robot Coverage of a Known Environment


Title	Efficient Multi-Robot Coverage of a Known Environment
Authors	Nare Karapetyan, Kelly Benson, Chris McKinney, Perouz Taslakian, Ioannis Rekleitis
Abstract	This paper addresses the complete area coverage problem of a known environment by multiple-robots. Complete area coverage is the problem of moving an end-effector over all available space while avoiding existing obstacles. In such tasks, using multiple robots can increase the efficiency of the area coverage in terms of minimizing the operational time and increase the robustness in the face of robot attrition. Unfortunately, the problem of finding an optimal solution for such an area coverage problem with multiple robots is known to be NP-complete. In this paper we present two approximation heuristics for solving the multi-robot coverage problem. The first solution presented is a direct extension of an efficient single robot area coverage algorithm, based on an exact cellular decomposition. The second algorithm is a greedy approach that divides the area into equal regions and applies an efficient single-robot coverage algorithm to each region. We present experimental results for two algorithms. Results indicate that our approaches provide good coverage distribution between robots and minimize the workload per robot, meanwhile ensuring complete coverage of the area.
Tasks
Published	2018-08-07
URL	http://arxiv.org/abs/1808.02541v1
PDF	http://arxiv.org/pdf/1808.02541v1.pdf
PWC	https://paperswithcode.com/paper/efficient-multi-robot-coverage-of-a-known
Repo
Framework

Correlation Heuristics for Constraint Programming


Title	Correlation Heuristics for Constraint Programming
Authors	Ruiwei Wang, Wei Xia, Roland H. C. Yap
Abstract	Effective general-purpose search strategies are an important component in Constraint Programming. We introduce a new idea, namely, using correlations between variables to guide search. Variable correlations are measured and maintained by using domain changes during constraint propagation. We propose two variable heuristics based on the correlation matrix, crbs-sum and crbs-max. We evaluate our correlation heuristics with well known heuristics, namely, dom/wdeg, impact-based search and activity-based search. Experiments on a large set of benchmarks show that our correlation heuristics are competitive with the other heuristics, and can be the fastest on many series.
Tasks
Published	2018-05-06
URL	http://arxiv.org/abs/1805.02205v2
PDF	http://arxiv.org/pdf/1805.02205v2.pdf
PWC	https://paperswithcode.com/paper/correlation-heuristics-for-constraint
Repo
Framework

DEFRAG: Deep Euclidean Feature Representations through Adaptation on the Grassmann Manifold


Title	DEFRAG: Deep Euclidean Feature Representations through Adaptation on the Grassmann Manifold
Authors	Breton Minnehan, Andreas Savakis
Abstract	We propose a novel technique for training deep networks with the objective of obtaining feature representations that exist in a Euclidean space and exhibit strong clustering behavior. Our desired features representations have three traits: they can be compared using a standard Euclidian distance metric, samples from the same class are tightly clustered, and samples from different classes are well separated. However, most deep networks do not enforce such feature representations. The DEFRAG training technique consists of two steps: first good feature clustering behavior is encouraged though an auxiliary loss function based on the Silhouette clustering metric. Then the feature space is retracted onto a Grassmann manifold to ensure that the L_2 Norm forms a similarity metric. The DEFRAG technique achieves state of the art results on standard classification datasets using a relatively small network architecture with significantly fewer parameters than many standard networks.
Tasks
Published	2018-06-20
URL	http://arxiv.org/abs/1806.07688v1
PDF	http://arxiv.org/pdf/1806.07688v1.pdf
PWC	https://paperswithcode.com/paper/defrag-deep-euclidean-feature-representations
Repo
Framework

Knowledge Compilation with Continuous Random Variables and its Application in Hybrid Probabilistic Logic Programming


Title	Knowledge Compilation with Continuous Random Variables and its Application in Hybrid Probabilistic Logic Programming
Authors	Pedro Zuidberg Dos Martires, Anton Dries, Luc De Raedt
Abstract	In probabilistic reasoning, the traditionally discrete domain has been elevated to the hybrid domain encompassing additionally continuous random variables. Inference in the hybrid domain, however, usually necessitates to condone trade-offs on either the inference on discrete or continuous random variables. We introduce a novel approach based on weighted model integration and algebraic model counting that circumvents these trade-offs. We then show how it supports knowledge compilation and exact probabilistic inference. Moreover, we introduce the hybrid probabilistic logic programming language HAL-ProbLog, an extension of ProbLog, to which we apply our inference approach.
Tasks
Published	2018-07-02
URL	http://arxiv.org/abs/1807.00614v2
PDF	http://arxiv.org/pdf/1807.00614v2.pdf
PWC	https://paperswithcode.com/paper/knowledge-compilation-with-continuous-random
Repo
Framework

Instance-level Sketch-based Retrieval by Deep Triplet Classification Siamese Network


Title	Instance-level Sketch-based Retrieval by Deep Triplet Classification Siamese Network
Authors	Peng Lu, Hangyu Lin, Yanwei Fu, Shaogang Gong, Yu-Gang Jiang, Xiangyang Xue
Abstract	Sketch has been employed as an effective communicative tool to express the abstract and intuitive meanings of object. Recognizing the free-hand sketch drawing is extremely useful in many real-world applications. While content-based sketch recognition has been studied for several decades, the instance-level Sketch-Based Image Retrieval (SBIR) tasks have attracted significant research attention recently. The existing datasets such as QMUL-Chair and QMUL-Shoe, focus on the retrieval tasks of chairs and shoes. However, there are several key limitations in previous instance-level SBIR works. The state-of-the-art works have to heavily rely on the pre-training process, quality of edge maps, multi-cropping testing strategy, and augmenting sketch images. To efficiently solve the instance-level SBIR, we propose a new Deep Triplet Classification Siamese Network (DeepTCNet) which employs DenseNet-169 as the basic feature extractor and is optimized by the triplet loss and classification loss. Critically, our proposed DeepTCNet can break the limitations existed in previous works. The extensive experiments on five benchmark sketch datasets validate the effectiveness of the proposed model. Additionally, to study the tasks of sketch-based hairstyle retrieval, this paper contributes a new instance-level photo-sketch dataset - Hairstyle Photo-Sketch dataset, which is composed of 3600 sketches and photos, and 2400 sketch-photo pairs.
Tasks	Image Retrieval, Sketch-Based Image Retrieval, Sketch Recognition
Published	2018-11-28
URL	https://arxiv.org/abs/1811.11375v2
PDF	https://arxiv.org/pdf/1811.11375v2.pdf
PWC	https://paperswithcode.com/paper/instance-level-sketch-based-retrieval-by-deep
Repo
Framework

On efficient global optimization via universal Kriging surrogate models


Title	On efficient global optimization via universal Kriging surrogate models
Authors	Pramudita Satria Palar, Koji Shimoyama
Abstract	In this paper, we investigate the capability of the universal Kriging (UK) model for single-objective global optimization applied within an efficient global optimization (EGO) framework. We implemented this combined UK-EGO framework and studied four variants of the UK methods, that is, a UK with a first-order polynomial, a UK with a second-order polynomial, a blind Kriging (BK) implementation from the ooDACE toolbox, and a polynomial-chaos Kriging (PCK) implementation. The UK-EGO framework with automatic trend function selection derived from the BK and PCK models works by building a UK surrogate model and then performing optimizations via expected improvement criteria on the Kriging model with the lowest leave-one-out cross-validation error. Next, we studied and compared the UK-EGO variants and standard EGO using five synthetic test functions and one aerodynamic problem. Our results show that the proper choice for the trend function through automatic feature selection can improve the optimization performance of UK-EGO relative to EGO. From our results, we found that PCK-EGO was the best variant, as it had more robust performance as compared to the rest of the UK-EGO schemes; however, total-order expansion should be used to generate the candidate trend function set for high-dimensional problems. Note that, for some test functions, the UK with predetermined polynomial trend functions performed better than that of BK and PCK, indicating that the use of automatic trend function selection does not always lead to the best quality solutions. We also found that although some variants of UK are not as globally accurate as the ordinary Kriging (OK), they can still identify better-optimized solutions due to the addition of the trend function, which helps the optimizer locate the global optimum.
Tasks	Feature Selection
Published	2018-03-23
URL	http://arxiv.org/abs/1803.08667v1
PDF	http://arxiv.org/pdf/1803.08667v1.pdf
PWC	https://paperswithcode.com/paper/on-efficient-global-optimization-via
Repo
Framework

Learning Effective RGB-D Representations for Scene Recognition


Title	Learning Effective RGB-D Representations for Scene Recognition
Authors	Xinhang Song, Shuqiang Jiang, Luis Herranz, Chengpeng Chen
Abstract	Deep convolutional networks (CNN) can achieve impressive results on RGB scene recognition thanks to large datasets such as Places. In contrast, RGB-D scene recognition is still underdeveloped in comparison, due to two limitations of RGB-D data we address in this paper. The first limitation is the lack of depth data for training deep learning models. Rather than fine tuning or transferring RGB-specific features, we address this limitation by proposing an architecture and a two-step training approach that directly learns effective depth-specific features using weak supervision via patches. The resulting RGB-D model also benefits from more complementary multimodal features. Another limitation is the short range of depth sensors (typically 0.5m to 5.5m), resulting in depth images not capturing distant objects in the scenes that RGB images can. We show that this limitation can be addressed by using RGB-D videos, where more comprehensive depth information is accumulated as the camera travels across the scene. Focusing on this scenario, we introduce the ISIA RGB-D video dataset to evaluate RGB-D scene recognition with videos. Our video recognition architecture combines convolutional and recurrent neural networks (RNNs) that are trained in three steps with increasingly complex data to learn effective features (i.e. patches, frames and sequences). Our approach obtains state-of-the-art performances on RGB-D image (NYUD2 and SUN RGB-D) and video (ISIA RGB-D) scene recognition.
Tasks	Scene Recognition, Video Recognition
Published	2018-09-17
URL	http://arxiv.org/abs/1809.06269v1
PDF	http://arxiv.org/pdf/1809.06269v1.pdf
PWC	https://paperswithcode.com/paper/learning-effective-rgb-d-representations-for
Repo
Framework

Melanoma Recognition with an Ensemble of Techniques for Segmentation and a Structural Analysis for Classification


Title	Melanoma Recognition with an Ensemble of Techniques for Segmentation and a Structural Analysis for Classification
Authors	Christoph Rasche
Abstract	An approach to lesion recognition is described that for lesion localization uses an ensemble of segmentation techniques and for lesion classification an exhaustive structural analysis. For localization, candidate regions are obtained from global thresholding of the chromatic maps and from applying the K-Means algorithm to the RGB image; the candidate regions are then integrated. For classification, a relatively exhaustive structural analysis of contours and regions is carried out.
Tasks
Published	2018-07-18
URL	http://arxiv.org/abs/1807.06905v1
PDF	http://arxiv.org/pdf/1807.06905v1.pdf
PWC	https://paperswithcode.com/paper/melanoma-recognition-with-an-ensemble-of
Repo
Framework

A Data-Driven Residential Transformer Overloading Risk Assessment Method


Title	A Data-Driven Residential Transformer Overloading Risk Assessment Method
Authors	Ming Dong, Benzhe Li, Alex Nassif
Abstract	Residential transformer population is a critical type of asset that many electric utility companies have been attempting to manage proactively and effectively to reduce unexpected failures and life losses that are often caused by transformer overloading. Within the typical power asset portfolio, the residential transformer asset is often large in population, having lowest reliability design, lacking transformer loading data and susceptible to customer loading behaviors such as adoption of distributed energy resources and electric vehicles. On the bright side, the availability of more residential operation data along with the advancement of data analytics techniques have provided a new path to further our understanding of local residential transformer overloading risks statistically. This research developed a new data-driven method to combine clustering analysis and the simulation of transformer temperature rise and insulation life loss to quantitatively and statistically assess the overloading risk of residential transformer population in one area and suggest proper risk management measures according to the assessment results. Case studies from an actual Canadian utility company have been presented and discussed in detail to demonstrate the applicability and usefulness of the proposed method.
Tasks
Published	2018-05-02
URL	http://arxiv.org/abs/1805.00630v2
PDF	http://arxiv.org/pdf/1805.00630v2.pdf
PWC	https://paperswithcode.com/paper/a-data-driven-residential-transformer
Repo
Framework

Adding Attentiveness to the Neurons in Recurrent Neural Networks


Title	Adding Attentiveness to the Neurons in Recurrent Neural Networks
Authors	Pengfei Zhang, Jianru Xue, Cuiling Lan, Wenjun Zeng, Zhanning Gao, Nanning Zheng
Abstract	Recurrent neural networks (RNNs) are capable of modeling the temporal dynamics of complex sequential information. However, the structures of existing RNN neurons mainly focus on controlling the contributions of current and historical information but do not explore the different importance levels of different elements in an input vector of a time slot. We propose adding a simple yet effective Element-wiseAttention Gate (EleAttG) to an RNN block (e.g., all RNN neurons in a network layer) that empowers the RNN neurons to have the attentiveness capability. For an RNN block, an EleAttG is added to adaptively modulate the input by assigning different levels of importance, i.e., attention, to each element/dimension of the input. We refer to an RNN block equipped with an EleAttG as an EleAtt-RNN block. Specifically, the modulation of the input is content adaptive and is performed at fine granularity, being element-wise rather than input-wise. The proposed EleAttG, as an additional fundamental unit, is general and can be applied to any RNN structures, e.g., standard RNN, Long Short-Term Memory (LSTM), or Gated Recurrent Unit (GRU). We demonstrate the effectiveness of the proposed EleAtt-RNN by applying it to the action recognition tasks on both 3D human skeleton data and RGB videos. Experiments show that adding attentiveness through EleAttGs to RNN blocks significantly boosts the power of RNNs.
Tasks	Skeleton Based Action Recognition, Temporal Action Localization
Published	2018-07-12
URL	http://arxiv.org/abs/1807.04445v1
PDF	http://arxiv.org/pdf/1807.04445v1.pdf
PWC	https://paperswithcode.com/paper/adding-attentiveness-to-the-neurons-in
Repo
Framework

DeSTNet: Densely Fused Spatial Transformer Networks


Title	DeSTNet: Densely Fused Spatial Transformer Networks
Authors	Roberto Annunziata, Christos Sagonas, Jacques Calì
Abstract	Modern Convolutional Neural Networks (CNN) are extremely powerful on a range of computer vision tasks. However, their performance may degrade when the data is characterised by large intra-class variability caused by spatial transformations. The Spatial Transformer Network (STN) is currently the method of choice for providing CNNs the ability to remove those transformations and improve performance in an end-to-end learning framework. In this paper, we propose Densely Fused Spatial Transformer Network (DeSTNet), which, to our best knowledge, is the first dense fusion pattern for combining multiple STNs. Specifically, we show how changing the connectivity pattern of multiple STNs from sequential to dense leads to more powerful alignment modules. Extensive experiments on three benchmarks namely, MNIST, GTSRB, and IDocDB show that the proposed technique outperforms related state-of-the-art methods (i.e., STNs and CSTNs) both in terms of accuracy and robustness.
Tasks
Published	2018-07-11
URL	http://arxiv.org/abs/1807.04050v2
PDF	http://arxiv.org/pdf/1807.04050v2.pdf
PWC	https://paperswithcode.com/paper/destnet-densely-fused-spatial-transformer
Repo
Framework

Deep Learning for Imbalance Data Classification using Class Expert Generative Adversarial Network


Title	Deep Learning for Imbalance Data Classification using Class Expert Generative Adversarial Network
Authors	Fanny, Tjeng Wawan Cenggoro
Abstract	Without any specific way for imbalance data classification, artificial intelligence algorithm cannot recognize data from minority classes easily. In general, modifying the existing algorithm by assuming that the training data is imbalanced, is the only way to handle imbalance data. However, for a normal data handling, this way mostly produces a deficient result. In this research, we propose a class expert generative adversarial network (CE-GAN) as the solution for imbalance data classification. CE-GAN is a modification in deep learning algorithm architecture that does not have an assumption that the training data is imbalance data. Moreover, CE-GAN is designed to identify more detail about the character of each class before classification step. CE-GAN has been proved in this research to give a good performance for imbalance data classification.
Tasks
Published	2018-07-12
URL	http://arxiv.org/abs/1807.04585v2
PDF	http://arxiv.org/pdf/1807.04585v2.pdf
PWC	https://paperswithcode.com/paper/deep-learning-for-imbalance-data
Repo
Framework

Deep PDF: Probabilistic Surface Optimization and Density Estimation


Title	Deep PDF: Probabilistic Surface Optimization and Density Estimation
Authors	Dmitry Kopitkov, Vadim Indelman
Abstract	A probability density function (pdf) encodes the entire stochastic knowledge about data distribution, where data may represent stochastic observations in robotics, transition state pairs in reinforcement learning or any other empirically acquired modality. Inferring data pdf is of prime importance, allowing to analyze various model hypotheses and perform smart decision making. However, most density estimation techniques are limited in their representation expressiveness to specific kernel type or predetermined distribution family, and have other restrictions. For example, kernel density estimation (KDE) methods require meticulous parameter search and are extremely slow at querying new points. In this paper we present a novel non-parametric density estimation approach, DeepPDF, that uses a neural network to approximate a target pdf given samples from thereof. Such a representation provides high inference accuracy for a wide range of target pdfs using a relatively simple network structure, making our method highly statistically robust. This is done via a new stochastic optimization algorithm, \emph{Probabilistic Surface Optimization} (PSO), that turns to advantage the stochastic nature of sample points in order to force network output to be identical to the output of a target pdf. Once trained, query point evaluation can be efficiently done in DeepPDF by a simple network forward pass, with linear complexity in the number of query points. Moreover, the PSO algorithm is capable of inferring the frequency of data samples and may also be used in other statistical tasks such as conditional estimation and distribution transformation. We compare the derived approach with KDE methods showing its superior performance and accuracy.
Tasks	Decision Making, Density Estimation, Stochastic Optimization
Published	2018-07-27
URL	http://arxiv.org/abs/1807.10728v2
PDF	http://arxiv.org/pdf/1807.10728v2.pdf
PWC	https://paperswithcode.com/paper/deep-pdf-probabilistic-surface-optimization
Repo
Framework