Paper Group ANR 482
Direction-aware Spatial Context Features for Shadow Detection and Removal. In-RDBMS Hardware Acceleration of Advanced Analytics. Generative Adversarial Networks and Perceptual Losses for Video Super-Resolution. Multiple Target Tracking by Learning Feature Representation and Distance Metric Jointly. Local Interpretable Model-agnostic Explanations of …
Direction-aware Spatial Context Features for Shadow Detection and Removal
| Title | Direction-aware Spatial Context Features for Shadow Detection and Removal |
| Authors | Xiaowei Hu, Chi-Wing Fu, Lei Zhu, Jing Qin, Pheng-Ann Heng |
| Abstract | Shadow detection and shadow removal are fundamental and challenging tasks, requiring an understanding of the global image semantics. This paper presents a novel deep neural network design for shadow detection and removal by analyzing the spatial image context in a direction-aware manner. To achieve this, we first formulate the direction-aware attention mechanism in a spatial recurrent neural network (RNN) by introducing attention weights when aggregating spatial context features in the RNN. By learning these weights through training, we can recover direction-aware spatial context (DSC) for detecting and removing shadows. This design is developed into the DSC module and embedded in a convolutional neural network (CNN) to learn the DSC features at different levels. Moreover, we design a weighted cross entropy loss to make effective the training for shadow detection and further adopt the network for shadow removal by using a Euclidean loss function and formulating a color transfer function to address the color and luminosity inconsistencies in the training pairs. We employed two shadow detection benchmark datasets and two shadow removal benchmark datasets, and performed various experiments to evaluate our method. Experimental results show that our method performs favorably against the state-of-the-art methods for both shadow detection and shadow removal. |
| Tasks | Shadow Detection, Shadow Detection And Removal |
| Published | 2018-05-12 |
| URL | https://arxiv.org/abs/1805.04635v2 |
| https://arxiv.org/pdf/1805.04635v2.pdf | |
| PWC | https://paperswithcode.com/paper/direction-aware-spatial-context-features-for-1 |
| Repo | |
| Framework | |
In-RDBMS Hardware Acceleration of Advanced Analytics
| Title | In-RDBMS Hardware Acceleration of Advanced Analytics |
| Authors | Divya Mahajan, Joon Kyung Kim, Jacob Sacks, Adel Ardalan, Arun Kumar, Hadi Esmaeilzadeh |
| Abstract | The data revolution is fueled by advances in machine learning, databases, and hardware design. Programmable accelerators are making their way into each of these areas independently. As such, there is a void of solutions that enables hardware acceleration at the intersection of these disjoint fields. This paper sets out to be the initial step towards a unifying solution for in-Database Acceleration of Advanced Analytics (DAnA). Deploying specialized hardware, such as FPGAs, for in-database analytics currently requires hand-designing the hardware and manually routing the data. Instead, DAnA automatically maps a high-level specification of advanced analytics queries to an FPGA accelerator. The accelerator implementation is generated for a User Defined Function (UDF), expressed as a part of an SQL query using a Python-embedded Domain-Specific Language (DSL). To realize an efficient in-database integration, DAnA accelerators contain a novel hardware structure, Striders, that directly interface with the buffer pool of the database. Striders extract, cleanse, and process the training data tuples that are consumed by a multi-threaded FPGA engine that executes the analytics algorithm. We integrate DAnA with PostgreSQL to generate hardware accelerators for a range of real-world and synthetic datasets running diverse ML algorithms. Results show that DAnA-enhanced PostgreSQL provides, on average, 8.3x end-to-end speedup for real datasets, with a maximum of 28.2x. Moreover, DAnA-enhanced PostgreSQL is, on average, 4.0x faster than the multi-threaded Apache MADLib running on Greenplum. DAnA provides these benefits while hiding the complexity of hardware design from data scientists and allowing them to express the algorithm in =30-60 lines of Python. |
| Tasks | |
| Published | 2018-01-08 |
| URL | http://arxiv.org/abs/1801.06027v2 |
| http://arxiv.org/pdf/1801.06027v2.pdf | |
| PWC | https://paperswithcode.com/paper/in-rdbms-hardware-acceleration-of-advanced |
| Repo | |
| Framework | |
Generative Adversarial Networks and Perceptual Losses for Video Super-Resolution
| Title | Generative Adversarial Networks and Perceptual Losses for Video Super-Resolution |
| Authors | Alice Lucas, Santiago Lopez Tapia, Rafael Molina, Aggelos K. Katsaggelos |
| Abstract | Video super-resolution (VSR) has become one of the most critical problems in video processing. In the deep learning literature, recent works have shown the benefits of using adversarial-based and perceptual losses to improve the performance on various image restoration tasks; however, these have yet to be applied for video super-resolution. In this work, we propose a Generative Adversarial Network(GAN)-based formulation for VSR. We introduce a new generator network optimized for the VSR problem, named VSRResNet, along with a new discriminator architecture to properly guide VSRResNet during the GAN training. We further enhance our VSR GAN formulation with two regularizers, a distance loss in feature-space and pixel-space, to obtain our final VSRResFeatGAN model. We show that pre-training our generator with the Mean-Squared-Error loss only quantitatively surpasses the current state-of-the-art VSR models. Finally, we employ the PercepDist metric (Zhang et al., 2018) to compare state-of-the-art VSR models. We show that this metric more accurately evaluates the perceptual quality of SR solutions obtained from neural networks, compared with the commonly used PSNR/SSIM metrics. Finally, we show that our proposed model, the VSRResFeatGAN model, outperforms current state-of-the-art SR models, both quantitatively and qualitatively. |
| Tasks | Image Restoration, Super-Resolution, Video Super-Resolution |
| Published | 2018-06-14 |
| URL | http://arxiv.org/abs/1806.05764v2 |
| http://arxiv.org/pdf/1806.05764v2.pdf | |
| PWC | https://paperswithcode.com/paper/generative-adversarial-networks-and |
| Repo | |
| Framework | |
Multiple Target Tracking by Learning Feature Representation and Distance Metric Jointly
| Title | Multiple Target Tracking by Learning Feature Representation and Distance Metric Jointly |
| Authors | Jun Xiang, Guoshuai Zhang, Jianhua Hou, Nong Sang, Rui Huang |
| Abstract | Designing a robust affinity model is the key issue in multiple target tracking (MTT). This paper proposes a novel affinity model by learning feature representation and distance metric jointly in a unified deep architecture. Specifically, we design a CNN network to obtain appearance cue tailored towards person Re-ID, and an LSTM network for motion cue to predict target position, respectively. Both cues are combined with a triplet loss function, which performs end-to-end learning of the fused features in a desired embedding space. Experiments in the challenging MOT benchmark demonstrate, that even by a simple Linear Assignment strategy fed with affinity scores of our method, very competitive results are achieved when compared with the most recent state-of-theart approaches. |
| Tasks | |
| Published | 2018-02-09 |
| URL | http://arxiv.org/abs/1802.03252v1 |
| http://arxiv.org/pdf/1802.03252v1.pdf | |
| PWC | https://paperswithcode.com/paper/multiple-target-tracking-by-learning-feature |
| Repo | |
| Framework | |
Local Interpretable Model-agnostic Explanations of Bayesian Predictive Models via Kullback-Leibler Projections
| Title | Local Interpretable Model-agnostic Explanations of Bayesian Predictive Models via Kullback-Leibler Projections |
| Authors | Tomi Peltola |
| Abstract | We introduce a method, KL-LIME, for explaining predictions of Bayesian predictive models by projecting the information in the predictive distribution locally to a simpler, interpretable explanation model. The proposed approach combines the recent Local Interpretable Model-agnostic Explanations (LIME) method with ideas from Bayesian projection predictive variable selection methods. The information theoretic basis helps in navigating the trade-off between explanation fidelity and complexity. We demonstrate the method in explaining MNIST digit classifications made by a Bayesian deep convolutional neural network. |
| Tasks | |
| Published | 2018-10-05 |
| URL | http://arxiv.org/abs/1810.02678v1 |
| http://arxiv.org/pdf/1810.02678v1.pdf | |
| PWC | https://paperswithcode.com/paper/local-interpretable-model-agnostic |
| Repo | |
| Framework | |
End-to-end Learning of a Convolutional Neural Network via Deep Tensor Decomposition
| Title | End-to-end Learning of a Convolutional Neural Network via Deep Tensor Decomposition |
| Authors | Samet Oymak, Mahdi Soltanolkotabi |
| Abstract | In this paper we study the problem of learning the weights of a deep convolutional neural network. We consider a network where convolutions are carried out over non-overlapping patches with a single kernel in each layer. We develop an algorithm for simultaneously learning all the kernels from the training data. Our approach dubbed Deep Tensor Decomposition (DeepTD) is based on a rank-1 tensor decomposition. We theoretically investigate DeepTD under a realizable model for the training data where the inputs are chosen i.i.d. from a Gaussian distribution and the labels are generated according to planted convolutional kernels. We show that DeepTD is data-efficient and provably works as soon as the sample size exceeds the total number of convolutional weights in the network. We carry out a variety of numerical experiments to investigate the effectiveness of DeepTD and verify our theoretical findings. |
| Tasks | |
| Published | 2018-05-16 |
| URL | http://arxiv.org/abs/1805.06523v1 |
| http://arxiv.org/pdf/1805.06523v1.pdf | |
| PWC | https://paperswithcode.com/paper/end-to-end-learning-of-a-convolutional-neural |
| Repo | |
| Framework | |
Supervised Deep Kriging for Single-Image Super-Resolution
| Title | Supervised Deep Kriging for Single-Image Super-Resolution |
| Authors | Gianni Franchi, Angela Yao, Andreas Kolb |
| Abstract | We propose a novel single-image super-resolution approach based on the geostatistical method of kriging. Kriging is a zero-bias minimum-variance estimator that performs spatial interpolation based on a weighted average of known observations. Rather than solving for the kriging weights via the traditional method of inverting covariance matrices, we propose a supervised form in which we learn a deep network to generate said weights. We combine the kriging weight generation and kriging process into a joint network that can be learned end-to-end. Our network achieves competitive super-resolution results as other state-of-the-art methods. In addition, since the super-resolution process follows a known statistical framework, we are able to estimate bias and variance, something which is rarely possible for other deep networks. |
| Tasks | Image Super-Resolution, Super-Resolution |
| Published | 2018-12-10 |
| URL | http://arxiv.org/abs/1812.04042v1 |
| http://arxiv.org/pdf/1812.04042v1.pdf | |
| PWC | https://paperswithcode.com/paper/supervised-deep-kriging-for-single-image |
| Repo | |
| Framework | |
Variational Inference for Gaussian Process with Panel Count Data
| Title | Variational Inference for Gaussian Process with Panel Count Data |
| Authors | Hongyi Ding, Young Lee, Issei Sato, Masashi Sugiyama |
| Abstract | We present the first framework for Gaussian-process-modulated Poisson processes when the temporal data appear in the form of panel counts. Panel count data frequently arise when experimental subjects are observed only at discrete time points and only the numbers of occurrences of the events between subsequent observation times are available. The exact occurrence timestamps of the events are unknown. The method of conducting the efficient variational inference is presented, based on the assumption of a Gaussian-process-modulated intensity function. We derive a tractable lower bound to alleviate the problems of the intractable evidence lower bound inherent in the variational inference framework. Our algorithm outperforms classical methods on both synthetic and three real panel count sets. |
| Tasks | |
| Published | 2018-03-12 |
| URL | http://arxiv.org/abs/1803.04232v1 |
| http://arxiv.org/pdf/1803.04232v1.pdf | |
| PWC | https://paperswithcode.com/paper/variational-inference-for-gaussian-process-1 |
| Repo | |
| Framework | |
Continuous Trade-off Optimization between Fast and Accurate Deep Face Detectors
| Title | Continuous Trade-off Optimization between Fast and Accurate Deep Face Detectors |
| Authors | Petru Soviany, Radu Tudor Ionescu |
| Abstract | Although deep neural networks offer better face detection results than shallow or handcrafted models, their complex architectures come with higher computational requirements and slower inference speeds than shallow neural networks. In this context, we study five straightforward approaches to achieve an optimal trade-off between accuracy and speed in face detection. All the approaches are based on separating the test images in two batches, an easy batch that is fed to a faster face detector and a difficult batch that is fed to a more accurate yet slower detector. We conduct experiments on the AFW and the FDDB data sets, using MobileNet-SSD as the fast face detector and S3FD (Single Shot Scale-invariant Face Detector) as the accurate face detector, both models being pre-trained on the WIDER FACE data set. Our experiments show that the proposed difficulty metrics compare favorably to a random split of the images. |
| Tasks | Face Detection |
| Published | 2018-11-27 |
| URL | http://arxiv.org/abs/1811.11582v1 |
| http://arxiv.org/pdf/1811.11582v1.pdf | |
| PWC | https://paperswithcode.com/paper/continuous-trade-off-optimization-between |
| Repo | |
| Framework | |
Gaussian-Induced Convolution for Graphs
| Title | Gaussian-Induced Convolution for Graphs |
| Authors | Jiatao Jiang, Zhen Cui, Chunyan Xu, Jian Yang |
| Abstract | Learning representation on graph plays a crucial role in numerous tasks of pattern recognition. Different from grid-shaped images/videos, on which local convolution kernels can be lattices, however, graphs are fully coordinate-free on vertices and edges. In this work, we propose a Gaussian-induced convolution (GIC) framework to conduct local convolution filtering on irregular graphs. Specifically, an edge-induced Gaussian mixture model is designed to encode variations of subgraph region by integrating edge information into weighted Gaussian models, each of which implicitly characterizes one component of subgraph variations. In order to coarsen a graph, we derive a vertex-induced Gaussian mixture model to cluster vertices dynamically according to the connection of edges, which is approximately equivalent to the weighted graph cut. We conduct our multi-layer graph convolution network on several public datasets of graph classification. The extensive experiments demonstrate that our GIC is effective and can achieve the state-of-the-art results. |
| Tasks | Graph Classification, Learning Representation On Graph |
| Published | 2018-11-11 |
| URL | http://arxiv.org/abs/1811.04393v1 |
| http://arxiv.org/pdf/1811.04393v1.pdf | |
| PWC | https://paperswithcode.com/paper/gaussian-induced-convolution-for-graphs |
| Repo | |
| Framework | |
On the potential for open-endedness in neural networks
| Title | On the potential for open-endedness in neural networks |
| Authors | Nicholas Guttenberg, Nathaniel Virgo, Alexandra Penn |
| Abstract | Natural evolution gives the impression of leading to an open-ended process of increasing diversity and complexity. If our goal is to produce such open-endedness artificially, this suggests an approach driven by evolutionary metaphor. On the other hand, techniques from machine learning and artificial intelligence are often considered too narrow to provide the sort of exploratory dynamics associated with evolution. In this paper, we hope to bridge that gap by reviewing common barriers to open-endedness in the evolution-inspired approach and how they are dealt with in the evolutionary case - collapse of diversity, saturation of complexity, and failure to form new kinds of individuality. We then show how these problems map onto similar issues in the machine learning approach, and discuss how the same insights and solutions which alleviated those barriers in evolutionary approaches can be ported over. At the same time, the form these issues take in the machine learning formulation suggests new ways to analyze and resolve barriers to open-endedness. Ultimately, we hope to inspire researchers to be able to interchangeably use evolutionary and gradient-descent-based machine learning methods to approach the design and creation of open-ended systems. |
| Tasks | |
| Published | 2018-12-12 |
| URL | http://arxiv.org/abs/1812.04907v1 |
| http://arxiv.org/pdf/1812.04907v1.pdf | |
| PWC | https://paperswithcode.com/paper/on-the-potential-for-open-endedness-in-neural |
| Repo | |
| Framework | |
Evaluating CBR Similarity Functions for BAM Switching in Networks with Dynamic Traffic Profile
| Title | Evaluating CBR Similarity Functions for BAM Switching in Networks with Dynamic Traffic Profile |
| Authors | Eliseu Oliveira, Rafael Freitas, Joberto Martins |
| Abstract | In an increasingly complex scenario for network management, a solution that allows configuration in more autonomous way with less intervention of the network manager is expected. This paper presents an evaluation of similarity functions that are necessary in the context of using a learning strategy for finding solutions. The learning approach considered is based on Case-Based Reasoning (CBR) and is applied to a network scenario where different Bandwidth Allocation Models (BAMs) behaviors are used and must be eventually switched looking for the best possible network operation. In this context, it is required to identify and configure an adequate similarity function that will be used in the learning process to recover similar solutions previously considered. This paper introduces the similarity functions, explains the relevant aspects of the learning process in which the similarity function plays a role and, finally, presents a proof of concept for a specific similarity function adopted. Results show that the similarity function was capable to get similar results from the existing use case database. As such, the use of similarity functions with CBR technique has proved to be potentially satisfactory for supporting BAM switching decisions mostly driven by the dynamics of input traffic profile. |
| Tasks | |
| Published | 2018-06-08 |
| URL | http://arxiv.org/abs/1806.03155v1 |
| http://arxiv.org/pdf/1806.03155v1.pdf | |
| PWC | https://paperswithcode.com/paper/evaluating-cbr-similarity-functions-for-bam |
| Repo | |
| Framework | |
Learning Device Models with Recurrent Neural Networks
| Title | Learning Device Models with Recurrent Neural Networks |
| Authors | John Clemens |
| Abstract | Recurrent neural networks (RNNs) are powerful constructs capable of modeling complex systems, up to and including Turing Machines. However, learning such complex models from finite training sets can be difficult. In this paper we empirically show that RNNs can learn models of computer peripheral devices through input and output state observation. This enables automated development of functional software-only models of hardware devices. Such models are applicable to any number of tasks, including device validation, driver development, code de-obfuscation, and reverse engineering. We show that the same RNN structure successfully models six different devices from simple test circuits up to a 16550 UART serial port, and verify that these models are capable of producing equivalent output to real hardware. |
| Tasks | |
| Published | 2018-05-21 |
| URL | http://arxiv.org/abs/1805.07869v1 |
| http://arxiv.org/pdf/1805.07869v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-device-models-with-recurrent-neural |
| Repo | |
| Framework | |
Handling Massive N-Gram Datasets Efficiently
| Title | Handling Massive N-Gram Datasets Efficiently |
| Authors | Giulio Ermanno Pibiri, Rossano Venturini |
| Abstract | This paper deals with the two fundamental problems concerning the handling of large n-gram language models: indexing, that is compressing the n-gram strings and associated satellite data without compromising their retrieval speed; and estimation, that is computing the probability distribution of the strings from a large textual source. Regarding the problem of indexing, we describe compressed, exact and lossless data structures that achieve, at the same time, high space reductions and no time degradation with respect to state-of-the-art solutions and related software packages. In particular, we present a compressed trie data structure in which each word following a context of fixed length k, i.e., its preceding k words, is encoded as an integer whose value is proportional to the number of words that follow such context. Since the number of words following a given context is typically very small in natural languages, we lower the space of representation to compression levels that were never achieved before. Despite the significant savings in space, our technique introduces a negligible penalty at query time. Regarding the problem of estimation, we present a novel algorithm for estimating modified Kneser-Ney language models, that have emerged as the de-facto choice for language modeling in both academia and industry, thanks to their relatively low perplexity performance. Estimating such models from large textual sources poses the challenge of devising algorithms that make a parsimonious use of the disk. The state-of-the-art algorithm uses three sorting steps in external memory: we show an improved construction that requires only one sorting step thanks to exploiting the properties of the extracted n-gram strings. With an extensive experimental analysis performed on billions of n-grams, we show an average improvement of 4.5X on the total running time of the state-of-the-art approach. |
| Tasks | Language Modelling |
| Published | 2018-06-25 |
| URL | https://arxiv.org/abs/1806.09447v2 |
| https://arxiv.org/pdf/1806.09447v2.pdf | |
| PWC | https://paperswithcode.com/paper/handling-massive-n-gram-datasets-efficiently |
| Repo | |
| Framework | |
A Generalized Vector Space Model for Ontology-Based Information Retrieval
| Title | A Generalized Vector Space Model for Ontology-Based Information Retrieval |
| Authors | Vuong M. Ngo, Tru H. Cao |
| Abstract | Named entities (NE) are objects that are referred to by names such as people, organizations and locations. Named entities and keywords are important to the meaning of a document. We propose a generalized vector space model that combines named entities and keywords. In the model, we take into account different ontological features of named entities, namely, aliases, classes and identifiers. Moreover, we use entity classes to represent the latent information of interrogative words in Wh-queries, which are ignored in traditional keyword-based searching. We have implemented and tested the proposed model on a TREC dataset, as presented and discussed in the paper. |
| Tasks | Information Retrieval |
| Published | 2018-07-20 |
| URL | http://arxiv.org/abs/1807.07779v1 |
| http://arxiv.org/pdf/1807.07779v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-generalized-vector-space-model-for-ontology |
| Repo | |
| Framework | |
