July 29, 2019

2958 words 14 mins read

Paper Group ANR 97

Automatic semantic role labeling on non-revised syntactic trees of journalistic texts. MSR-net:Low-light Image Enhancement Using Deep Convolutional Network. Nonlinear Embedding Transform for Unsupervised Domain Adaptation. A Bio-Inspired Multi-Exposure Fusion Framework for Low-light Image Enhancement. Nestrov’s Acceleration For Second Order Method. …

Automatic semantic role labeling on non-revised syntactic trees of journalistic texts


Title	Automatic semantic role labeling on non-revised syntactic trees of journalistic texts
Authors	Nathan Siegle Hartmann, Magali Sanches Duran, Sandra Maria Aluísio
Abstract	Semantic Role Labeling (SRL) is a Natural Language Processing task that enables the detection of events described in sentences and the participants of these events. For Brazilian Portuguese (BP), there are two studies recently concluded that perform SRL in journalistic texts. [1] obtained F1-measure scores of 79.6, using the PropBank.Br corpus, which has syntactic trees manually revised, [8], without using a treebank for training, obtained F1-measure scores of 68.0 for the same corpus. However, the use of manually revised syntactic trees for this task does not represent a real scenario of application. The goal of this paper is to evaluate the performance of SRL on revised and non-revised syntactic trees using a larger and balanced corpus of BP journalistic texts. First, we have shown that [1]‘s system also performs better than [8]‘s system on the larger corpus. Second, the SRL system trained on non-revised syntactic trees performs better over non-revised trees than a system trained on gold-standard data.
Tasks	Semantic Role Labeling
Published	2017-04-10
URL	http://arxiv.org/abs/1704.03016v1
PDF	http://arxiv.org/pdf/1704.03016v1.pdf
PWC	https://paperswithcode.com/paper/automatic-semantic-role-labeling-on-non
Repo
Framework

MSR-net:Low-light Image Enhancement Using Deep Convolutional Network


Title	MSR-net:Low-light Image Enhancement Using Deep Convolutional Network
Authors	Liang Shen, Zihan Yue, Fan Feng, Quan Chen, Shihao Liu, Jie Ma
Abstract	Images captured in low-light conditions usually suffer from very low contrast, which increases the difficulty of subsequent computer vision tasks in a great extent. In this paper, a low-light image enhancement model based on convolutional neural network and Retinex theory is proposed. Firstly, we show that multi-scale Retinex is equivalent to a feedforward convolutional neural network with different Gaussian convolution kernels. Motivated by this fact, we consider a Convolutional Neural Network(MSR-net) that directly learns an end-to-end mapping between dark and bright images. Different fundamentally from existing approaches, low-light image enhancement in this paper is regarded as a machine learning problem. In this model, most of the parameters are optimized by back-propagation, while the parameters of traditional models depend on the artificial setting. Experiments on a number of challenging images reveal the advantages of our method in comparison with other state-of-the-art methods from the qualitative and quantitative perspective.
Tasks	Image Enhancement, Low-Light Image Enhancement
Published	2017-11-07
URL	http://arxiv.org/abs/1711.02488v1
PDF	http://arxiv.org/pdf/1711.02488v1.pdf
PWC	https://paperswithcode.com/paper/msr-netlow-light-image-enhancement-using-deep
Repo
Framework

Nonlinear Embedding Transform for Unsupervised Domain Adaptation


Title	Nonlinear Embedding Transform for Unsupervised Domain Adaptation
Authors	Hemanth Venkateswara, Shayok Chakraborty, Sethuraman Panchanathan
Abstract	The problem of domain adaptation (DA) deals with adapting classifier models trained on one data distribution to different data distributions. In this paper, we introduce the Nonlinear Embedding Transform (NET) for unsupervised DA by combining domain alignment along with similarity-based embedding. We also introduce a validation procedure to estimate the model parameters for the NET algorithm using the source data. Comprehensive evaluations on multiple vision datasets demonstrate that the NET algorithm outperforms existing competitive procedures for unsupervised DA.
Tasks	Domain Adaptation, Unsupervised Domain Adaptation
Published	2017-06-22
URL	http://arxiv.org/abs/1706.07524v1
PDF	http://arxiv.org/pdf/1706.07524v1.pdf
PWC	https://paperswithcode.com/paper/nonlinear-embedding-transform-for
Repo
Framework

A Bio-Inspired Multi-Exposure Fusion Framework for Low-light Image Enhancement


Title	A Bio-Inspired Multi-Exposure Fusion Framework for Low-light Image Enhancement
Authors	Zhenqiang Ying, Ge Li, Wen Gao
Abstract	Low-light images are not conducive to human observation and computer vision algorithms due to their low visibility. Although many image enhancement techniques have been proposed to solve this problem, existing methods inevitably introduce contrast under- and over-enhancement. Inspired by human visual system, we design a multi-exposure fusion framework for low-light image enhancement. Based on the framework, we propose a dual-exposure fusion algorithm to provide an accurate contrast and lightness enhancement. Specifically, we first design the weight matrix for image fusion using illumination estimation techniques. Then we introduce our camera response model to synthesize multi-exposure images. Next, we find the best exposure ratio so that the synthetic image is well-exposed in the regions where the original image is under-exposed. Finally, the enhanced result is obtained by fusing the input image and the synthetic image according to the weight matrix. Experiments show that our method can obtain results with less contrast and lightness distortion compared to that of several state-of-the-art methods.
Tasks	Image Enhancement, Low-Light Image Enhancement
Published	2017-11-02
URL	http://arxiv.org/abs/1711.00591v1
PDF	http://arxiv.org/pdf/1711.00591v1.pdf
PWC	https://paperswithcode.com/paper/a-bio-inspired-multi-exposure-fusion
Repo
Framework

Nestrov’s Acceleration For Second Order Method


Title	Nestrov’s Acceleration For Second Order Method
Authors	Haishan Ye, Zhihua Zhang
Abstract	Optimization plays a key role in machine learning. Recently, stochastic second-order methods have attracted much attention due to their low computational cost in each iteration. However, these algorithms might perform poorly especially if it is hard to approximate the Hessian well and efficiently. As far as we know, there is no effective way to handle this problem. In this paper, we resort to Nestrov’s acceleration technique to improve the convergence performance of a class of second-order methods called approximate Newton. We give a theoretical analysis that Nestrov’s acceleration technique can improve the convergence performance for approximate Newton just like for first-order methods. We accordingly propose an accelerated regularized sub-sampled Newton. Our accelerated algorithm performs much better than the original regularized sub-sampled Newton in experiments, which validates our theory empirically. Besides, the accelerated regularized sub-sampled Newton has good performance comparable to or even better than state-of-art algorithms.
Tasks
Published	2017-05-19
URL	http://arxiv.org/abs/1705.07171v2
PDF	http://arxiv.org/pdf/1705.07171v2.pdf
PWC	https://paperswithcode.com/paper/nestrovs-acceleration-for-second-order-method
Repo
Framework

GibbsNet: Iterative Adversarial Inference for Deep Graphical Models


Title	GibbsNet: Iterative Adversarial Inference for Deep Graphical Models
Authors	Alex Lamb, Devon Hjelm, Yaroslav Ganin, Joseph Paul Cohen, Aaron Courville, Yoshua Bengio
Abstract	Directed latent variable models that formulate the joint distribution as $p(x,z) = p(z) p(x \mid z)$ have the advantage of fast and exact sampling. However, these models have the weakness of needing to specify $p(z)$, often with a simple fixed prior that limits the expressiveness of the model. Undirected latent variable models discard the requirement that $p(z)$ be specified with a prior, yet sampling from them generally requires an iterative procedure such as blocked Gibbs-sampling that may require many steps to draw samples from the joint distribution $p(x, z)$. We propose a novel approach to learning the joint distribution between the data and a latent code which uses an adversarially learned iterative procedure to gradually refine the joint distribution, $p(x, z)$, to better match with the data distribution on each step. GibbsNet is the best of both worlds both in theory and in practice. Achieving the speed and simplicity of a directed latent variable model, it is guaranteed (assuming the adversarial game reaches the virtual training criteria global minimum) to produce samples from $p(x, z)$ with only a few sampling iterations. Achieving the expressiveness and flexibility of an undirected latent variable model, GibbsNet does away with the need for an explicit $p(z)$ and has the ability to do attribute prediction, class-conditional generation, and joint image-attribute modeling in a single model which is not trained for any of these specific tasks. We show empirically that GibbsNet is able to learn a more complex $p(z)$ and show that this leads to improved inpainting and iterative refinement of $p(x, z)$ for dozens of steps and stable generation without collapse for thousands of steps, despite being trained on only a few steps.
Tasks	Latent Variable Models
Published	2017-12-12
URL	http://arxiv.org/abs/1712.04120v1
PDF	http://arxiv.org/pdf/1712.04120v1.pdf
PWC	https://paperswithcode.com/paper/gibbsnet-iterative-adversarial-inference-for
Repo
Framework

Automatic Leaf Extraction from Outdoor Images


Title	Automatic Leaf Extraction from Outdoor Images
Authors	N. Anantrasirichai, Sion Hannuna, Nishan Canagarajah
Abstract	Automatic plant recognition and disease analysis may be streamlined by an image of a complete, isolated leaf as an initial input. Segmenting leaves from natural images is a hard problem. Cluttered and complex backgrounds: often composed of other leaves are commonplace. Furthermore, their appearance is highly dependent upon illumination and viewing perspective. In order to address these issues we propose a methodology which exploits the leaves venous systems in tandem with other low level features. Background and leaf markers are created using colour, intensity and texture. Two approaches are investigated: watershed and graph-cut and results compared. Primary-secondary vein detection and a protrusion-notch removal are applied to refine the extracted leaf. The efficacy of our approach is demonstrated against existing work.
Tasks
Published	2017-09-19
URL	http://arxiv.org/abs/1709.06437v1
PDF	http://arxiv.org/pdf/1709.06437v1.pdf
PWC	https://paperswithcode.com/paper/automatic-leaf-extraction-from-outdoor-images
Repo
Framework

Secure SURF with Fully Homomorphic Encryption


Title	Secure SURF with Fully Homomorphic Encryption
Authors	Thomas Shortell, Ali Shokoufandeh
Abstract	Cloud computing is an important part of today’s world because offloading computations is a method to reduce costs. In this paper, we investigate computing the Speeded Up Robust Features (SURF) using Fully Homomorphic Encryption (FHE). Performing SURF in FHE enables a method to offload the computations while maintaining security and privacy of the original data. In support of this research, we developed a framework to compute SURF via a rational number based compatible with FHE. Although floating point (R) to rational numbers (Q) conversion introduces error, our research provides tight bounds on the magnitude of error in terms of parameters of FHE. We empirically verified the proposed method against a set of images at different sizes and showed that our framework accurately computes most of the SURF keypoints in FHE.
Tasks
Published	2017-07-19
URL	http://arxiv.org/abs/1707.05905v1
PDF	http://arxiv.org/pdf/1707.05905v1.pdf
PWC	https://paperswithcode.com/paper/secure-surf-with-fully-homomorphic-encryption
Repo
Framework

Context-Aware Single-Shot Detector


Title	Context-Aware Single-Shot Detector
Authors	Wei Xiang, Dong-Qing Zhang, Heather Yu, Vassilis Athitsos
Abstract	SSD is one of the state-of-the-art object detection algorithms, and it combines high detection accuracy with real-time speed. However, it is widely recognized that SSD is less accurate in detecting small objects compared to large objects, because it ignores the context from outside the proposal boxes. In this paper, we present CSSD–a shorthand for context-aware single-shot multibox object detector. CSSD is built on top of SSD, with additional layers modeling multi-scale contexts. We describe two variants of CSSD, which differ in their context layers, using dilated convolution layers (DiCSSD) and deconvolution layers (DeCSSD) respectively. The experimental results show that the multi-scale context modeling significantly improves the detection accuracy. In addition, we study the relationship between effective receptive fields (ERFs) and the theoretical receptive fields (TRFs), particularly on a VGGNet. The empirical results further strengthen our conclusion that SSD coupled with context layers achieves better detection results especially for small objects ($+3.2% {\rm AP}_{@0.5}$ on MS-COCO compared to the newest SSD), while maintaining comparable runtime performance.
Tasks	Object Detection
Published	2017-07-27
URL	http://arxiv.org/abs/1707.08682v2
PDF	http://arxiv.org/pdf/1707.08682v2.pdf
PWC	https://paperswithcode.com/paper/context-aware-single-shot-detector
Repo
Framework

Where is my forearm? Clustering of body parts from simultaneous tactile and linguistic input using sequential mapping


Title	Where is my forearm? Clustering of body parts from simultaneous tactile and linguistic input using sequential mapping
Authors	Karla Stepanova, Matej Hoffmann, Zdenek Straka, Frederico B. Klein, Angelo Cangelosi, Michal Vavrecka
Abstract	Humans and animals are constantly exposed to a continuous stream of sensory information from different modalities. At the same time, they form more compressed representations like concepts or symbols. In species that use language, this process is further structured by this interaction, where a mapping between the sensorimotor concepts and linguistic elements needs to be established. There is evidence that children might be learning language by simply disambiguating potential meanings based on multiple exposures to utterances in different contexts (cross-situational learning). In existing models, the mapping between modalities is usually found in a single step by directly using frequencies of referent and meaning co-occurrences. In this paper, we present an extension of this one-step mapping and introduce a newly proposed sequential mapping algorithm together with a publicly available Matlab implementation. For demonstration, we have chosen a less typical scenario: instead of learning to associate objects with their names, we focus on body representations. A humanoid robot is receiving tactile stimulations on its body, while at the same time listening to utterances of the body part names (e.g., hand, forearm and torso). With the goal at arriving at the correct “body categories”, we demonstrate how a sequential mapping algorithm outperforms one-step mapping. In addition, the effect of data set size and noise in the linguistic input are studied.
Tasks
Published	2017-06-08
URL	http://arxiv.org/abs/1706.02490v1
PDF	http://arxiv.org/pdf/1706.02490v1.pdf
PWC	https://paperswithcode.com/paper/where-is-my-forearm-clustering-of-body-parts
Repo
Framework

Multi-Mention Learning for Reading Comprehension with Neural Cascades


Title	Multi-Mention Learning for Reading Comprehension with Neural Cascades
Authors	Swabha Swayamdipta, Ankur P. Parikh, Tom Kwiatkowski
Abstract	Reading comprehension is a challenging task, especially when executed across longer or across multiple evidence documents, where the answer is likely to reoccur. Existing neural architectures typically do not scale to the entire evidence, and hence, resort to selecting a single passage in the document (either via truncation or other means), and carefully searching for the answer within that passage. However, in some cases, this strategy can be suboptimal, since by focusing on a specific passage, it becomes difficult to leverage multiple mentions of the same answer throughout the document. In this work, we take a different approach by constructing lightweight models that are combined in a cascade to find the answer. Each submodel consists only of feed-forward networks equipped with an attention mechanism, making it trivially parallelizable. We show that our approach can scale to approximately an order of magnitude larger evidence documents and can aggregate information at the representation level from multiple mentions of each answer candidate across the document. Empirically, our approach achieves state-of-the-art performance on both the Wikipedia and web domains of the TriviaQA dataset, outperforming more complex, recurrent architectures.
Tasks	Reading Comprehension
Published	2017-11-02
URL	http://arxiv.org/abs/1711.00894v2
PDF	http://arxiv.org/pdf/1711.00894v2.pdf
PWC	https://paperswithcode.com/paper/multi-mention-learning-for-reading
Repo
Framework

Metalearning for Feature Selection


Title	Metalearning for Feature Selection
Authors	Ben Goertzel, Nil Geisweiller, Chris Poulin
Abstract	A general formulation of optimization problems in which various candidate solutions may use different feature-sets is presented, encompassing supervised classification, automated program learning and other cases. A novel characterization of the concept of a “good quality feature” for such an optimization problem is provided; and a proposal regarding the integration of quality based feature selection into metalearning is suggested, wherein the quality of a feature for a problem is estimated using knowledge about related features in the context of related problems. Results are presented regarding extensive testing of this “feature metalearning” approach on supervised text classification problems; it is demonstrated that, in this context, feature metalearning can provide significant and sometimes dramatic speedup over standard feature selection heuristics.
Tasks	Feature Selection, Text Classification
Published	2017-03-20
URL	http://arxiv.org/abs/1703.06990v1
PDF	http://arxiv.org/pdf/1703.06990v1.pdf
PWC	https://paperswithcode.com/paper/metalearning-for-feature-selection
Repo
Framework

DecideNet: Counting Varying Density Crowds Through Attention Guided Detection and Density Estimation


Title	DecideNet: Counting Varying Density Crowds Through Attention Guided Detection and Density Estimation
Authors	Jiang Liu, Chenqiang Gao, Deyu Meng, Alexander G. Hauptmann
Abstract	In real-world crowd counting applications, the crowd densities vary greatly in spatial and temporal domains. A detection based counting method will estimate crowds accurately in low density scenes, while its reliability in congested areas is downgraded. A regression based approach, on the other hand, captures the general density information in crowded regions. Without knowing the location of each person, it tends to overestimate the count in low density areas. Thus, exclusively using either one of them is not sufficient to handle all kinds of scenes with varying densities. To address this issue, a novel end-to-end crowd counting framework, named DecideNet (DEteCtIon and Density Estimation Network) is proposed. It can adaptively decide the appropriate counting mode for different locations on the image based on its real density conditions. DecideNet starts with estimating the crowd density by generating detection and regression based density maps separately. To capture inevitable variation in densities, it incorporates an attention module, meant to adaptively assess the reliability of the two types of estimations. The final crowd counts are obtained with the guidance of the attention module to adopt suitable estimations from the two kinds of density maps. Experimental results show that our method achieves state-of-the-art performance on three challenging crowd counting datasets.
Tasks	Crowd Counting, Density Estimation
Published	2017-12-18
URL	http://arxiv.org/abs/1712.06679v2
PDF	http://arxiv.org/pdf/1712.06679v2.pdf
PWC	https://paperswithcode.com/paper/decidenet-counting-varying-density-crowds
Repo
Framework

Is Structure Necessary for Modeling Argument Expectations in Distributional Semantics?


Title	Is Structure Necessary for Modeling Argument Expectations in Distributional Semantics?
Authors	Emmanuele Chersoni, Enrico Santus, Philippe Blache, Alessandro Lenci
Abstract	Despite the number of NLP studies dedicated to thematic fit estimation, little attention has been paid to the related task of composing and updating verb argument expectations. The few exceptions have mostly modeled this phenomenon with structured distributional models, implicitly assuming a similarly structured representation of events. Recent experimental evidence, however, suggests that human processing system could also exploit an unstructured “bag-of-arguments” type of event representation to predict upcoming input. In this paper, we re-implement a traditional structured model and adapt it to compare the different hypotheses concerning the degree of structure in our event knowledge, evaluating their relative performance in the task of the argument expectations update.
Tasks
Published	2017-10-03
URL	http://arxiv.org/abs/1710.00998v1
PDF	http://arxiv.org/pdf/1710.00998v1.pdf
PWC	https://paperswithcode.com/paper/is-structure-necessary-for-modeling-argument
Repo
Framework

ParaGraphE: A Library for Parallel Knowledge Graph Embedding


Title	ParaGraphE: A Library for Parallel Knowledge Graph Embedding
Authors	Xiao-Fan Niu, Wu-Jun Li
Abstract	Knowledge graph embedding aims at translating the knowledge graph into numerical representations by transforming the entities and relations into continuous low-dimensional vectors. Recently, many methods [1, 5, 3, 2, 6] have been proposed to deal with this problem, but existing single-thread implementations of them are time-consuming for large-scale knowledge graphs. Here, we design a unified parallel framework to parallelize these methods, which achieves a significant time reduction without influencing the accuracy. We name our framework as ParaGraphE, which provides a library for parallel knowledge graph embedding. The source code can be downloaded from https://github.com/LIBBLE/LIBBLE-MultiThread/tree/master/ParaGraphE .
Tasks	Graph Embedding, Knowledge Graph Embedding, Knowledge Graphs
Published	2017-03-16
URL	http://arxiv.org/abs/1703.05614v3
PDF	http://arxiv.org/pdf/1703.05614v3.pdf
PWC	https://paperswithcode.com/paper/paragraphe-a-library-for-parallel-knowledge
Repo
Framework