July 28, 2019

2985 words 15 mins read

Paper Group ANR 339

Just DIAL: DomaIn Alignment Layers for Unsupervised Domain Adaptation. World Literature According to Wikipedia: Introduction to a DBpedia-Based Framework. Photorealistic Facial Expression Synthesis by the Conditional Difference Adversarial Autoencoder. Remote sensing of forests using discrete return airborne LiDAR. Scale Adaptive Clustering of Mult …

Just DIAL: DomaIn Alignment Layers for Unsupervised Domain Adaptation


Title	Just DIAL: DomaIn Alignment Layers for Unsupervised Domain Adaptation
Authors	Fabio Maria Carlucci, Lorenzo Porzi, Barbara Caputo, Elisa Ricci, Samuel Rota Bulò
Abstract	The empirical fact that classifiers, trained on given data collections, perform poorly when tested on data acquired in different settings is theoretically explained in domain adaptation through a shift among distributions of the source and target domains. Alleviating the domain shift problem, especially in the challenging setting where no labeled data are available for the target domain, is paramount for having visual recognition systems working in the wild. As the problem stems from a shift among distributions, intuitively one should try to align them. In the literature, this has resulted in a stream of works attempting to align the feature representations learned from the source and target domains. Here we take a different route. Rather than introducing regularization terms aiming to promote the alignment of the two representations, we act at the distribution level through the introduction of \emph{DomaIn Alignment Layers} (\DIAL), able to match the observed source and target data distributions to a reference one. Thorough experiments on three different public benchmarks we confirm the power of our approach.
Tasks	Domain Adaptation, Unsupervised Domain Adaptation
Published	2017-02-21
URL	http://arxiv.org/abs/1702.06332v3
PDF	http://arxiv.org/pdf/1702.06332v3.pdf
PWC	https://paperswithcode.com/paper/just-dial-domain-alignment-layers-for
Repo
Framework

World Literature According to Wikipedia: Introduction to a DBpedia-Based Framework


Title	World Literature According to Wikipedia: Introduction to a DBpedia-Based Framework
Authors	Christoph Hube, Frank Fischer, Robert Jäschke, Gerhard Lauer, Mads Rosendahl Thomsen
Abstract	Among the manifold takes on world literature, it is our goal to contribute to the discussion from a digital point of view by analyzing the representation of world literature in Wikipedia with its millions of articles in hundreds of languages. As a preliminary, we introduce and compare three different approaches to identify writers on Wikipedia using data from DBpedia, a community project with the goal of extracting and providing structured information from Wikipedia. Equipped with our basic set of writers, we analyze how they are represented throughout the 15 biggest Wikipedia language versions. We combine intrinsic measures (mostly examining the connectedness of articles) with extrinsic ones (analyzing how often articles are frequented by readers) and develop methods to evaluate our results. The better part of our findings seems to convey a rather conservative, old-fashioned version of world literature, but a version derived from reproducible facts revealing an implicit literary canon based on the editing and reading behavior of millions of people. While still having to solve some known issues, the introduced methods will help us build an observatory of world literature to further investigate its representativeness and biases.
Tasks
Published	2017-01-04
URL	http://arxiv.org/abs/1701.00991v1
PDF	http://arxiv.org/pdf/1701.00991v1.pdf
PWC	https://paperswithcode.com/paper/world-literature-according-to-wikipedia
Repo
Framework

Photorealistic Facial Expression Synthesis by the Conditional Difference Adversarial Autoencoder


Title	Photorealistic Facial Expression Synthesis by the Conditional Difference Adversarial Autoencoder
Authors	Yuqian Zhou, Bertram Emil Shi
Abstract	Photorealistic facial expression synthesis from single face image can be widely applied to face recognition, data augmentation for emotion recognition or entertainment. This problem is challenging, in part due to a paucity of labeled facial expression data, making it difficult for algorithms to disambiguate changes due to identity and changes due to expression. In this paper, we propose the conditional difference adversarial autoencoder, CDAAE, for facial expression synthesis. The CDAAE takes a facial image of a previously unseen person and generates an image of that human face with a target emotion or facial action unit label. The CDAAE adds a feedforward path to an autoencoder structure connecting low level features at the encoder to features at the corresponding level at the decoder. It handles the problem of disambiguating changes due to identity and changes due to facial expression by learning to generate the difference between low-level features of images of the same person but with different facial expressions. The CDAAE structure can be used to generate novel expressions by combining and interpolating between facial expressions/action units within the training set. Our experimental results demonstrate that the CDAAE can preserve identity information when generating facial expression for unseen subjects more faithfully than previous approaches. This is especially advantageous when training with small databases.
Tasks	Data Augmentation, Emotion Recognition, Face Recognition
Published	2017-08-30
URL	http://arxiv.org/abs/1708.09126v1
PDF	http://arxiv.org/pdf/1708.09126v1.pdf
PWC	https://paperswithcode.com/paper/photorealistic-facial-expression-synthesis-by
Repo
Framework

Remote sensing of forests using discrete return airborne LiDAR


Title	Remote sensing of forests using discrete return airborne LiDAR
Authors	Hamid Hamraz, Marco A. Contreras
Abstract	Airborne discrete return light detection and ranging (LiDAR) point clouds covering forested areas can be processed to segment individual trees and retrieve their morphological attributes. Segmenting individual trees in natural deciduous forests however remained a challenge because of the complex and multi-layered canopy. In this chapter, we present (i) a robust segmentation method that avoids a priori assumptions about the canopy structure, (ii) a vertical canopy stratification procedure that improves segmentation of understory trees, (iii) an occlusion model for estimating the point density of each canopy stratum, and (iv) a distributed computing approach for efficient processing at the forest level. When applied to the University of Kentucky Robinson Forest, the segmentation method detected about 90% of overstory and 47% of understory trees with over-segmentation rates of 14% and 2%. Stratifying the canopy improved the detection rate of understory trees to 68% at the cost of increasing their over-segmentations to 16%. According to our occlusion model, a point density of ~170 pt/m-sqr is needed to segment understory trees as accurately as overstory trees. Lastly, using the distributed approach, we segmented about two million trees in the 7,440-ha forest in 2.5 hours using 192 processors, which is 167 times faster than using a single processor. Keywords: individual tree segmentation, multi-layered stand, vertical canopy stratification, segmentation evaluation, point density, canopy occlusion effect, big data, distributed computing.
Tasks
Published	2017-07-17
URL	http://arxiv.org/abs/1707.09865v1
PDF	http://arxiv.org/pdf/1707.09865v1.pdf
PWC	https://paperswithcode.com/paper/remote-sensing-of-forests-using-discrete
Repo
Framework

Scale Adaptive Clustering of Multiple Structures


Title	Scale Adaptive Clustering of Multiple Structures
Authors	Xiang Yang, Peter Meer
Abstract	We propose the segmentation of noisy datasets into Multiple Inlier Structures with a new Robust Estimator (MISRE). The scale of each individual structure is estimated adaptively from the input data and refined by mean shift, without tuning any parameter in the process, or manually specifying thresholds for different estimation problems. Once all the data points were classified into separate structures, these structures are sorted by their densities with the strongest inlier structures coming out first. Several 2D and 3D synthetic and real examples are presented to illustrate the efficiency, robustness and the limitations of the MISRE algorithm.
Tasks
Published	2017-09-26
URL	http://arxiv.org/abs/1709.09550v1
PDF	http://arxiv.org/pdf/1709.09550v1.pdf
PWC	https://paperswithcode.com/paper/scale-adaptive-clustering-of-multiple
Repo
Framework

ANSAC: Adaptive Non-minimal Sample and Consensus


Title	ANSAC: Adaptive Non-minimal Sample and Consensus
Authors	Victor Fragoso, Chris Sweeney, Pradeep Sen, Matthew Turk
Abstract	While RANSAC-based methods are robust to incorrect image correspondences (outliers), their hypothesis generators are not robust to correct image correspondences (inliers) with positional error (noise). This slows down their convergence because hypotheses drawn from a minimal set of noisy inliers can deviate significantly from the optimal model. This work addresses this problem by introducing ANSAC, a RANSAC-based estimator that accounts for noise by adaptively using more than the minimal number of correspondences required to generate a hypothesis. ANSAC estimates the inlier ratio (the fraction of correct correspondences) of several ranked subsets of candidate correspondences and generates hypotheses from them. Its hypothesis-generation mechanism prioritizes the use of subsets with high inlier ratio to generate high-quality hypotheses. ANSAC uses an early termination criterion that keeps track of the inlier ratio history and terminates when it has not changed significantly for a period of time. The experiments show that ANSAC finds good homography and fundamental matrix estimates in a few iterations, consistently outperforming state-of-the-art methods.
Tasks
Published	2017-09-27
URL	http://arxiv.org/abs/1709.09559v1
PDF	http://arxiv.org/pdf/1709.09559v1.pdf
PWC	https://paperswithcode.com/paper/ansac-adaptive-non-minimal-sample-and
Repo
Framework

Subjective Knowledge Acquisition and Enrichment Powered By Crowdsourcing


Title	Subjective Knowledge Acquisition and Enrichment Powered By Crowdsourcing
Authors	Rui Meng, Hao Xin, Lei Chen, Yangqiu Song
Abstract	Knowledge bases (KBs) have attracted increasing attention due to its great success in various areas, such as Web and mobile search.Existing KBs are restricted to objective factual knowledge, such as city population or fruit shape, whereas,subjective knowledge, such as big city, which is commonly mentioned in Web and mobile queries, has been neglected. Subjective knowledge differs from objective knowledge in that it has no documented or observed ground truth. Instead, the truth relies on people’s dominant opinion. Thus, we can use the crowdsourcing technique to get opinion from the crowd. In our work, we propose a system, called crowdsourced subjective knowledge acquisition (CoSKA),for subjective knowledge acquisition powered by crowdsourcing and existing KBs. The acquired knowledge can be used to enrich existing KBs in the subjective dimension which bridges the gap between existing objective knowledge and subjective queries.The main challenge of CoSKA is the conflict between large scale knowledge facts and limited crowdsourcing resource. To address this challenge, in this work, we define knowledge inference rules and then select the seed knowledge judiciously for crowdsourcing to maximize the inference power under the resource constraint. Our experimental results on real knowledge base and crowdsourcing platform verify the effectiveness of CoSKA system.
Tasks
Published	2017-05-16
URL	http://arxiv.org/abs/1705.05720v1
PDF	http://arxiv.org/pdf/1705.05720v1.pdf
PWC	https://paperswithcode.com/paper/subjective-knowledge-acquisition-and
Repo
Framework

Network of Recurrent Neural Networks


Title	Network of Recurrent Neural Networks
Authors	Chao-Ming Wang
Abstract	We describe a class of systems theory based neural networks called “Network Of Recurrent neural networks” (NOR), which introduces a new structure level to RNN related models. In NOR, RNNs are viewed as the high-level neurons and are used to build the high-level layers. More specifically, we propose several methodologies to design different NOR topologies according to the theory of system evolution. Then we carry experiments on three different tasks to evaluate our implementations. Experimental results show our models outperform simple RNN remarkably under the same number of parameters, and sometimes achieve even better results than GRU and LSTM.
Tasks
Published	2017-10-10
URL	http://arxiv.org/abs/1710.03414v1
PDF	http://arxiv.org/pdf/1710.03414v1.pdf
PWC	https://paperswithcode.com/paper/network-of-recurrent-neural-networks
Repo
Framework

MUFold-SS: Protein Secondary Structure Prediction Using Deep Inception-Inside-Inception Networks


Title	MUFold-SS: Protein Secondary Structure Prediction Using Deep Inception-Inside-Inception Networks
Authors	Chao Fang, Yi Shang, Dong Xu
Abstract	Motivation: Protein secondary structure prediction can provide important information for protein 3D structure prediction and protein functions. Deep learning, which has been successfully applied to various research fields such as image classification and voice recognition, provides a new opportunity to significantly improve the secondary structure prediction accuracy. Although several deep-learning methods have been developed for secondary structure prediction, there is room for improvement. MUFold-SS was developed to address these issues. Results: Here, a very deep neural network, the deep inception-inside-inception networks (Deep3I), is proposed for protein secondary structure prediction and a software tool was implemented using this network. This network takes two inputs: a protein sequence and a profile generated by PSI-BLAST. The output is the predicted eight states (Q8) or three states (Q3) of secondary structures. The proposed Deep3I not only achieves the state-of-the-art performance but also runs faster than other tools. Deep3I achieves Q3 82.8% and Q8 71.1% accuracies on the CB513 benchmark.
Tasks	Image Classification, Protein Secondary Structure Prediction
Published	2017-09-12
URL	http://arxiv.org/abs/1709.06165v1
PDF	http://arxiv.org/pdf/1709.06165v1.pdf
PWC	https://paperswithcode.com/paper/mufold-ss-protein-secondary-structure
Repo
Framework

Semi-Supervised Learning for Detecting Human Trafficking


Title	Semi-Supervised Learning for Detecting Human Trafficking
Authors	Hamidreza Alvari, Paulo Shakarian, J. E. Kelly Snyder
Abstract	Human trafficking is one of the most atrocious crimes and among the challenging problems facing law enforcement which demands attention of global magnitude. In this study, we leverage textual data from the website “Backpage”- used for classified advertisement- to discern potential patterns of human trafficking activities which manifest online and identify advertisements of high interest to law enforcement. Due to the lack of ground truth, we rely on a human analyst from law enforcement, for hand-labeling a small portion of the crawled data. We extend the existing Laplacian SVM and present S3VM-R, by adding a regularization term to exploit exogenous information embedded in our feature space in favor of the task at hand. We train the proposed method using labeled and unlabeled data and evaluate it on a fraction of the unlabeled data, herein referred to as unseen data, with our expert’s further verification. Results from comparisons between our method and other semi-supervised and supervised approaches on the labeled data demonstrate that our learner is effective in identifying advertisements of high interest to law enforcement
Tasks
Published	2017-05-30
URL	http://arxiv.org/abs/1705.10786v1
PDF	http://arxiv.org/pdf/1705.10786v1.pdf
PWC	https://paperswithcode.com/paper/semi-supervised-learning-for-detecting-human
Repo
Framework

Bias Correction with Jackknife, Bootstrap, and Taylor Series


Title	Bias Correction with Jackknife, Bootstrap, and Taylor Series
Authors	Jiantao Jiao, Yanjun Han
Abstract	We analyze bias correction methods using jackknife, bootstrap, and Taylor series. We focus on the binomial model, and consider the problem of bias correction for estimating $f(p)$, where $f \in C[0,1]$ is arbitrary. We characterize the supremum norm of the bias of general jackknife and bootstrap estimators for any continuous functions, and demonstrate the in delete-$d$ jackknife, different values of $d$ may lead to drastically different behaviors in jackknife. We show that in the binomial model, iterating the bootstrap bias correction infinitely many times may lead to divergence of bias and variance, and demonstrate that the bias properties of the bootstrap bias corrected estimator after $r-1$ rounds are of the same order as that of the $r$-jackknife estimator if a bounded coefficients condition is satisfied.
Tasks
Published	2017-09-18
URL	https://arxiv.org/abs/1709.06183v3
PDF	https://arxiv.org/pdf/1709.06183v3.pdf
PWC	https://paperswithcode.com/paper/bias-correction-with-jackknife-bootstrap-and
Repo
Framework

Semi-Supervised AUC Optimization based on Positive-Unlabeled Learning


Title	Semi-Supervised AUC Optimization based on Positive-Unlabeled Learning
Authors	Tomoya Sakai, Gang Niu, Masashi Sugiyama
Abstract	Maximizing the area under the receiver operating characteristic curve (AUC) is a standard approach to imbalanced classification. So far, various supervised AUC optimization methods have been developed and they are also extended to semi-supervised scenarios to cope with small sample problems. However, existing semi-supervised AUC optimization methods rely on strong distributional assumptions, which are rarely satisfied in real-world problems. In this paper, we propose a novel semi-supervised AUC optimization method that does not require such restrictive assumptions. We first develop an AUC optimization method based only on positive and unlabeled data (PU-AUC) and then extend it to semi-supervised learning by combining it with a supervised AUC optimization method. We theoretically prove that, without the restrictive distributional assumptions, unlabeled data contribute to improving the generalization performance in PU and semi-supervised AUC optimization methods. Finally, we demonstrate the practical usefulness of the proposed methods through experiments.
Tasks
Published	2017-05-04
URL	http://arxiv.org/abs/1705.01708v2
PDF	http://arxiv.org/pdf/1705.01708v2.pdf
PWC	https://paperswithcode.com/paper/semi-supervised-auc-optimization-based-on
Repo
Framework

Robust Detection of Covariate-Treatment Interactions in Clinical Trials


Title	Robust Detection of Covariate-Treatment Interactions in Clinical Trials
Authors	Baptiste Goujaud, Eric W. Tramel, Pierre Courtiol, Mikhail Zaslavskiy, Gilles Wainrib
Abstract	Detection of interactions between treatment effects and patient descriptors in clinical trials is critical for optimizing the drug development process. The increasing volume of data accumulated in clinical trials provides a unique opportunity to discover new biomarkers and further the goal of personalized medicine, but it also requires innovative robust biomarker detection methods capable of detecting non-linear, and sometimes weak, signals. We propose a set of novel univariate statistical tests, based on the theory of random walks, which are able to capture non-linear and non-monotonic covariate-treatment interactions. We also propose a novel combined test, which leverages the power of all of our proposed univariate tests into a single general-case tool. We present results for both synthetic trials as well as real-world clinical trials, where we compare our method with state-of-the-art techniques and demonstrate the utility and robustness of our approach.
Tasks
Published	2017-12-21
URL	http://arxiv.org/abs/1712.08211v1
PDF	http://arxiv.org/pdf/1712.08211v1.pdf
PWC	https://paperswithcode.com/paper/robust-detection-of-covariate-treatment
Repo
Framework

Temporal scale selection in time-causal scale space


Title	Temporal scale selection in time-causal scale space
Authors	Tony Lindeberg
Abstract	When designing and developing scale selection mechanisms for generating hypotheses about characteristic scales in signals, it is essential that the selected scale levels reflect the extent of the underlying structures in the signal. This paper presents a theory and in-depth theoretical analysis about the scale selection properties of methods for automatically selecting local temporal scales in time-dependent signals based on local extrema over temporal scales of scale-normalized temporal derivative responses. Specifically, this paper develops a novel theoretical framework for performing such temporal scale selection over a time-causal and time-recursive temporal domain as is necessary when processing continuous video or audio streams in real time or when modelling biological perception. For a recently developed time-causal and time-recursive scale-space concept defined by convolution with a scale-invariant limit kernel, we show that it is possible to transfer a large number of the desirable scale selection properties that hold for the Gaussian scale-space concept over a non-causal temporal domain to this temporal scale-space concept over a truly time-causal domain. Specifically, we show that for this temporal scale-space concept, it is possible to achieve true temporal scale invariance although the temporal scale levels have to be discrete, which is a novel theoretical construction.
Tasks
Published	2017-01-09
URL	http://arxiv.org/abs/1701.05088v1
PDF	http://arxiv.org/pdf/1701.05088v1.pdf
PWC	https://paperswithcode.com/paper/temporal-scale-selection-in-time-causal-scale
Repo
Framework

Implicit Gradient Neural Networks with a Positive-Definite Mass Matrix for Online Linear Equations Solving


Title	Implicit Gradient Neural Networks with a Positive-Definite Mass Matrix for Online Linear Equations Solving
Authors	Ke Chen
Abstract	Motivated by the advantages achieved by implicit analogue net for solving online linear equations, a novel implicit neural model is designed based on conventional explicit gradient neural networks in this letter by introducing a positive-definite mass matrix. In addition to taking the advantages of the implicit neural dynamics, the proposed implicit gradient neural networks can still achieve globally exponential convergence to the unique theoretical solution of linear equations and also global stability even under no-solution and multi-solution situations. Simulative results verify theoretical convergence analysis on the proposed neural dynamics.
Tasks
Published	2017-03-17
URL	http://arxiv.org/abs/1703.05955v1
PDF	http://arxiv.org/pdf/1703.05955v1.pdf
PWC	https://paperswithcode.com/paper/implicit-gradient-neural-networks-with-a
Repo
Framework