Paper Group ANR 1612
Partially Linear Additive Gaussian Graphical Models. Optimal Clustering with Missing Values. Estimating multi-class dynamic origin-destination demand through a forward-backward algorithm on computational graphs. Revisiting Image Aesthetic Assessment via Self-Supervised Feature Learning. Uncoupled Regression from Pairwise Comparison Data. Multilingu …
Partially Linear Additive Gaussian Graphical Models
| Title | Partially Linear Additive Gaussian Graphical Models |
| Authors | Sinong Geng, Minhao Yan, Mladen Kolar, Oluwasanmi Koyejo |
| Abstract | We propose a partially linear additive Gaussian graphical model (PLA-GGM) for the estimation of associations between random variables distorted by observed confounders. Model parameters are estimated using an $L_1$-regularized maximal pseudo-profile likelihood estimator (MaPPLE) for which we prove $\sqrt{n}$-sparsistency. Importantly, our approach avoids parametric constraints on the effects of confounders on the estimated graphical model structure. Empirically, the PLA-GGM is applied to both synthetic and real-world datasets, demonstrating superior performance compared to competing methods. |
| Tasks | |
| Published | 2019-06-08 |
| URL | https://arxiv.org/abs/1906.03362v1 |
| https://arxiv.org/pdf/1906.03362v1.pdf | |
| PWC | https://paperswithcode.com/paper/partially-linear-additive-gaussian-graphical |
| Repo | |
| Framework | |
Optimal Clustering with Missing Values
| Title | Optimal Clustering with Missing Values |
| Authors | Shahin Boluki, Siamak Zamani Dadaneh, Xiaoning Qian, Edward R. Dougherty |
| Abstract | Missing values frequently arise in modern biomedical studies due to various reasons, including missing tests or complex profiling technologies for different omics measurements. Missing values can complicate the application of clustering algorithms, whose goals are to group points based on some similarity criterion. A common practice for dealing with missing values in the context of clustering is to first impute the missing values, and then apply the clustering algorithm on the completed data. We consider missing values in the context of optimal clustering, which finds an optimal clustering operator with reference to an underlying random labeled point process (RLPP). We show how the missing-value problem fits neatly into the overall framework of optimal clustering by incorporating the missing value mechanism into the random labeled point process and then marginalizing out the missing-value process. In particular, we demonstrate the proposed framework for the Gaussian model with arbitrary covariance structures. Comprehensive experimental studies on both synthetic and real-world RNA-seq data show the superior performance of the proposed optimal clustering with missing values when compared to various clustering approaches. Optimal clustering with missing values obviates the need for imputation-based pre-processing of the data, while at the same time possessing smaller clustering errors. |
| Tasks | Imputation |
| Published | 2019-02-26 |
| URL | http://arxiv.org/abs/1902.09694v1 |
| http://arxiv.org/pdf/1902.09694v1.pdf | |
| PWC | https://paperswithcode.com/paper/optimal-clustering-with-missing-values |
| Repo | |
| Framework | |
Estimating multi-class dynamic origin-destination demand through a forward-backward algorithm on computational graphs
| Title | Estimating multi-class dynamic origin-destination demand through a forward-backward algorithm on computational graphs |
| Authors | Wei Ma, Xidong Pi, Sean Qian |
| Abstract | Transportation networks are unprecedentedly complex with heterogeneous vehicular flow. Conventionally, vehicle classes are considered by vehicle classifications (such as standard passenger cars and trucks). However, vehicle flow heterogeneity stems from many other aspects in general, e.g., ride-sourcing vehicles versus personal vehicles, human driven vehicles versus connected and automated vehicles. Provided with some observations of vehicular flow for each class in a large-scale transportation network, how to estimate the multi-class spatio-temporal vehicular flow, in terms of time-varying Origin-Destination (OD) demand and path/link flow, remains a big challenge. This paper presents a solution framework for multi-class dynamic OD demand estimation (MCDODE) in large-scale networks. The proposed framework is built on a computational graph with tensor representations of spatio-temporal flow and all intermediate features involved in the MCDODE formulation. A forward-backward algorithm is proposed to efficiently solve the MCDODE formulation on computational graphs. In addition, we propose a novel concept of tree-based cumulative curves to estimate the gradient of OD demand. A Growing Tree algorithm is developed to construct tree-based cumulative curves. The proposed framework is examined on a small network as well as a real-world large-scale network. The experiment results indicate that the proposed framework is compelling, satisfactory and computationally plausible. |
| Tasks | |
| Published | 2019-03-12 |
| URL | http://arxiv.org/abs/1903.04681v1 |
| http://arxiv.org/pdf/1903.04681v1.pdf | |
| PWC | https://paperswithcode.com/paper/estimating-multi-class-dynamic-origin |
| Repo | |
| Framework | |
Revisiting Image Aesthetic Assessment via Self-Supervised Feature Learning
| Title | Revisiting Image Aesthetic Assessment via Self-Supervised Feature Learning |
| Authors | Kekai Sheng, Weiming Dong, Menglei Chai, Guohui Wang, Peng Zhou, Feiyue Huang, Bao-Gang Hu, Rongrong Ji, Chongyang Ma |
| Abstract | Visual aesthetic assessment has been an active research field for decades. Although latest methods have achieved promising performance on benchmark datasets, they typically rely on a large number of manual annotations including both aesthetic labels and related image attributes. In this paper, we revisit the problem of image aesthetic assessment from the self-supervised feature learning perspective. Our motivation is that a suitable feature representation for image aesthetic assessment should be able to distinguish different expert-designed image manipulations, which have close relationships with negative aesthetic effects. To this end, we design two novel pretext tasks to identify the types and parameters of editing operations applied to synthetic instances. The features from our pretext tasks are then adapted for a one-layer linear classifier to evaluate the performance in terms of binary aesthetic classification. We conduct extensive quantitative experiments on three benchmark datasets and demonstrate that our approach can faithfully extract aesthetics-aware features and outperform alternative pretext schemes. Moreover, we achieve comparable results to state-of-the-art supervised methods that use 10 million labels from ImageNet. |
| Tasks | |
| Published | 2019-11-26 |
| URL | https://arxiv.org/abs/1911.11419v1 |
| https://arxiv.org/pdf/1911.11419v1.pdf | |
| PWC | https://paperswithcode.com/paper/revisiting-image-aesthetic-assessment-via |
| Repo | |
| Framework | |
Uncoupled Regression from Pairwise Comparison Data
| Title | Uncoupled Regression from Pairwise Comparison Data |
| Authors | Liyuan Xu, Junya Honda, Gang Niu, Masashi Sugiyama |
| Abstract | Uncoupled regression is the problem to learn a model from unlabeled data and the set of target values while the correspondence between them is unknown. Such a situation arises in predicting anonymized targets that involve sensitive information, e.g., one’s annual income. Since existing methods for uncoupled regression often require strong assumptions on the true target function, and thus, their range of applications is limited, we introduce a novel framework that does not require such assumptions in this paper. Our key idea is to utilize pairwise comparison data, which consists of pairs of unlabeled data that we know which one has a larger target value. Such pairwise comparison data is easy to collect, as typically discussed in the learning-to-rank scenario, and does not break the anonymity of data. We propose two practical methods for uncoupled regression from pairwise comparison data and show that the learned regression model converges to the optimal model with the optimal parametric convergence rate when the target variable distributes uniformly. Moreover, we empirically show that for linear models the proposed methods are comparable to ordinary supervised regression with labeled data. |
| Tasks | Learning-To-Rank |
| Published | 2019-05-31 |
| URL | https://arxiv.org/abs/1905.13659v2 |
| https://arxiv.org/pdf/1905.13659v2.pdf | |
| PWC | https://paperswithcode.com/paper/uncoupled-regression-from-pairwise-comparison |
| Repo | |
| Framework | |
Multilingual Neural Machine Translation for Zero-Resource Languages
| Title | Multilingual Neural Machine Translation for Zero-Resource Languages |
| Authors | Surafel M. Lakew, Marcello Federico, Matteo Negri, Marco Turchi |
| Abstract | In recent years, Neural Machine Translation (NMT) has been shown to be more effective than phrase-based statistical methods, thus quickly becoming the state of the art in machine translation (MT). However, NMT systems are limited in translating low-resourced languages, due to the significant amount of parallel data that is required to learn useful mappings between languages. In this work, we show how the so-called multilingual NMT can help to tackle the challenges associated with low-resourced language translation. The underlying principle of multilingual NMT is to force the creation of hidden representations of words in a shared semantic space across multiple languages, thus enabling a positive parameter transfer across languages. Along this direction, we present multilingual translation experiments with three languages (English, Italian, Romanian) covering six translation directions, utilizing both recurrent neural networks and transformer (or self-attentive) neural networks. We then focus on the zero-shot translation problem, that is how to leverage multi-lingual data in order to learn translation directions that are not covered by the available training material. To this aim, we introduce our recently proposed iterative self-training method, which incrementally improves a multilingual NMT on a zero-shot direction by just relying on monolingual data. Our results on TED talks data show that multilingual NMT outperforms conventional bilingual NMT, that the transformer NMT outperforms recurrent NMT, and that zero-shot NMT outperforms conventional pivoting methods and even matches the performance of a fully-trained bilingual system. |
| Tasks | Machine Translation |
| Published | 2019-09-16 |
| URL | https://arxiv.org/abs/1909.07342v1 |
| https://arxiv.org/pdf/1909.07342v1.pdf | |
| PWC | https://paperswithcode.com/paper/multilingual-neural-machine-translation-for |
| Repo | |
| Framework | |
(De)Constructing Bias on Skin Lesion Datasets
| Title | (De)Constructing Bias on Skin Lesion Datasets |
| Authors | Alceu Bissoto, Michel Fornaciali, Eduardo Valle, Sandra Avila |
| Abstract | Melanoma is the deadliest form of skin cancer. Automated skin lesion analysis plays an important role for early detection. Nowadays, the ISIC Archive and the Atlas of Dermoscopy dataset are the most employed skin lesion sources to benchmark deep-learning based tools. However, all datasets contain biases, often unintentional, due to how they were acquired and annotated. Those biases distort the performance of machine-learning models, creating spurious correlations that the models can unfairly exploit, or, contrarily destroying cogent correlations that the models could learn. In this paper, we propose a set of experiments that reveal both types of biases, positive and negative, in existing skin lesion datasets. Our results show that models can correctly classify skin lesion images without clinically-meaningful information: disturbingly, the machine-learning model learned over images where no information about the lesion remains, presents an accuracy above the AI benchmark curated with dermatologists’ performances. That strongly suggests spurious correlations guiding the models. We fed models with additional clinically meaningful information, which failed to improve the results even slightly, suggesting the destruction of cogent correlations. Our main findings raise awareness of the limitations of models trained and evaluated in small datasets such as the ones we evaluated, and may suggest future guidelines for models intended for real-world deployment. |
| Tasks | |
| Published | 2019-04-18 |
| URL | http://arxiv.org/abs/1904.08818v1 |
| http://arxiv.org/pdf/1904.08818v1.pdf | |
| PWC | https://paperswithcode.com/paper/deconstructing-bias-on-skin-lesion-datasets |
| Repo | |
| Framework | |
Deep Tone Mapping Operator for High Dynamic Range Images
| Title | Deep Tone Mapping Operator for High Dynamic Range Images |
| Authors | Aakanksha Rana, Praveer Singh, Giuseppe Valenzise, Frederic Dufaux, Nikos Komodakis, Aljosa Smolic |
| Abstract | A computationally fast tone mapping operator (TMO) that can quickly adapt to a wide spectrum of high dynamic range (HDR) content is quintessential for visualization on varied low dynamic range (LDR) output devices such as movie screens or standard displays. Existing TMOs can successfully tone-map only a limited number of HDR content and require an extensive parameter tuning to yield the best subjective-quality tone-mapped output. In this paper, we address this problem by proposing a fast, parameter-free and scene-adaptable deep tone mapping operator (DeepTMO) that yields a high-resolution and high-subjective quality tone mapped output. Based on conditional generative adversarial network (cGAN), DeepTMO not only learns to adapt to vast scenic-content (e.g., outdoor, indoor, human, structures, etc.) but also tackles the HDR related scene-specific challenges such as contrast and brightness, while preserving the fine-grained details. We explore 4 possible combinations of Generator-Discriminator architectural designs to specifically address some prominent issues in HDR related deep-learning frameworks like blurring, tiling patterns and saturation artifacts. By exploring different influences of scales, loss-functions and normalization layers under a cGAN setting, we conclude with adopting a multi-scale model for our task. To further leverage on the large-scale availability of unlabeled HDR data, we train our network by generating targets using an objective HDR quality metric, namely Tone Mapping Image Quality Index (TMQI). We demonstrate results both quantitatively and qualitatively, and showcase that our DeepTMO generates high-resolution, high-quality output images over a large spectrum of real-world scenes. Finally, we evaluate the perceived quality of our results by conducting a pair-wise subjective study which confirms the versatility of our method. |
| Tasks | |
| Published | 2019-08-12 |
| URL | https://arxiv.org/abs/1908.04197v1 |
| https://arxiv.org/pdf/1908.04197v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-tone-mapping-operator-for-high-dynamic |
| Repo | |
| Framework | |
Advancements in Image Classification using Convolutional Neural Network
| Title | Advancements in Image Classification using Convolutional Neural Network |
| Authors | Farhana Sultana, A. Sufian, Paramartha Dutta |
| Abstract | Convolutional Neural Network (CNN) is the state-of-the-art for image classification task. Here we have briefly discussed different components of CNN. In this paper, We have explained different CNN architectures for image classification. Through this paper, we have shown advancements in CNN from LeNet-5 to latest SENet model. We have discussed the model description and training details of each model. We have also drawn a comparison among those models. |
| Tasks | Image Classification |
| Published | 2019-05-08 |
| URL | https://arxiv.org/abs/1905.03288v1 |
| https://arxiv.org/pdf/1905.03288v1.pdf | |
| PWC | https://paperswithcode.com/paper/190503288 |
| Repo | |
| Framework | |
3D Objectness Estimation via Bottom-up Regret Grouping
| Title | 3D Objectness Estimation via Bottom-up Regret Grouping |
| Authors | Zelin Ye, Yan Hao, Liang Xu, Rui Zhu, Cewu Lu |
| Abstract | 3D objectness estimation, namely discovering semantic objects from 3D scene, is a challenging and significant task in 3D understanding. In this paper, we propose a 3D objectness method working in a bottom-up manner. Beginning with over-segmented 3D segments, we iteratively group them into object proposals by learning an ingenious grouping predictor to determine whether two 3D segments can be grouped or not. To enhance robustness, a novel regret mechanism is presented to withdraw incorrect grouping operations. Hence the irreparable consequences brought by mistaken grouping in prior bottom-up works can be greatly reduced. Our experiments show that our method outperforms state-of-the-art 3D objectness methods with a small number of proposals in two difficult datasets, GMU-kitchen and CTD. Further ablation study also demonstrates the effectiveness of our grouping predictor and regret mechanism. |
| Tasks | |
| Published | 2019-12-05 |
| URL | https://arxiv.org/abs/1912.02332v1 |
| https://arxiv.org/pdf/1912.02332v1.pdf | |
| PWC | https://paperswithcode.com/paper/3d-objectness-estimation-via-bottom-up-regret |
| Repo | |
| Framework | |
A Context-Aware Approach for Detecting Check-Worthy Claims in Political Debates
| Title | A Context-Aware Approach for Detecting Check-Worthy Claims in Political Debates |
| Authors | Pepa Gencheva, Ivan Koychev, Lluís Màrquez, Alberto Barrón-Cedeño, Preslav Nakov |
| Abstract | In the context of investigative journalism, we address the problem of automatically identifying which claims in a given document are most worthy and should be prioritized for fact-checking. Despite its importance, this is a relatively understudied problem. Thus, we create a new dataset of political debates, containing statements that have been fact-checked by nine reputable sources, and we train machine learning models to predict which claims should be prioritized for fact-checking, i.e., we model the problem as a ranking task. Unlike previous work, which has looked primarily at sentences in isolation, in this paper we focus on a rich input representation modeling the context: relationship between the target statement and the larger context of the debate, interaction between the opponents, and reaction by the moderator and by the public. Our experiments show state-of-the-art results, outperforming a strong rivaling system by a margin, while also confirming the importance of the contextual information. |
| Tasks | |
| Published | 2019-12-14 |
| URL | https://arxiv.org/abs/1912.08084v1 |
| https://arxiv.org/pdf/1912.08084v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-context-aware-approach-for-detecting-check |
| Repo | |
| Framework | |
Towards Robust Relational Causal Discovery
| Title | Towards Robust Relational Causal Discovery |
| Authors | Sanghack Lee, Vasant Honavar |
| Abstract | We consider the problem of learning causal relationships from relational data. Existing approaches rely on queries to a relational conditional independence (RCI) oracle to establish and orient causal relations in such a setting. In practice, queries to a RCI oracle have to be replaced by reliable tests for RCI against available data. Relational data present several unique challenges in testing for RCI. We study the conditions under which traditional iid-based conditional independence (CI) tests yield reliable answers to RCI queries against relational data. We show how to conduct CI tests against relational data to robustly recover the underlying relational causal structure. Results of our experiments demonstrate the effectiveness of our proposed approach. |
| Tasks | Causal Discovery |
| Published | 2019-12-05 |
| URL | https://arxiv.org/abs/1912.02390v1 |
| https://arxiv.org/pdf/1912.02390v1.pdf | |
| PWC | https://paperswithcode.com/paper/towards-robust-relational-causal-discovery |
| Repo | |
| Framework | |
Twins Recognition Using Hierarchical Score Level Fusion
| Title | Twins Recognition Using Hierarchical Score Level Fusion |
| Authors | Cihan Akin, Umit Kacar, Murvet Kirci |
| Abstract | With the development of technology, the usage areas and importance of biometric systems have started to increase. Since the characteristics of each person are different from each other, a single model biometric system can yield successful results. However, because the characteristics of twin people are very close to each other, multiple biometric systems including multiple characteristics of individuals will be more appropriate and will increase the recognition rate. In this study, a multiple biometric recognition system consisting of a combination of multiple algorithms and multiple models was developed to distinguish people from other people and their twins. Ear and voice biometric data were used for the multimodal model and 38 pair of twin ear images and sound recordings were used in the data set. Sound and ear recognition rates were obtained using classical (hand-crafted) and deep learning algorithms. The results obtained were combined with the hierarchical score level fusion method to achieve a success rate of 94.74% in rank-1 and 100% in rank -2. |
| Tasks | |
| Published | 2019-10-27 |
| URL | https://arxiv.org/abs/1911.05625v1 |
| https://arxiv.org/pdf/1911.05625v1.pdf | |
| PWC | https://paperswithcode.com/paper/twins-recognition-using-hierarchical-score |
| Repo | |
| Framework | |
Deep Learning Models for Global Coordinate Transformations that Linearize PDEs
| Title | Deep Learning Models for Global Coordinate Transformations that Linearize PDEs |
| Authors | Craig Gin, Bethany Lusch, Steven L. Brunton, J. Nathan Kutz |
| Abstract | We develop a deep autoencoder architecture that can be used to find a coordinate transformation which turns a nonlinear PDE into a linear PDE. Our architecture is motivated by the linearizing transformations provided by the Cole-Hopf transform for Burgers equation and the inverse scattering transform for completely integrable PDEs. By leveraging a residual network architecture, a near-identity transformation can be exploited to encode intrinsic coordinates in which the dynamics are linear. The resulting dynamics are given by a Koopman operator matrix $\mathbf{K}$. The decoder allows us to transform back to the original coordinates as well. Multiple time step prediction can be performed by repeated multiplication by the matrix $\mathbf{K}$ in the intrinsic coordinates. We demonstrate our method on a number of examples, including the heat equation and Burgers equation, as well as the substantially more challenging Kuramoto-Sivashinsky equation, showing that our method provides a robust architecture for discovering interpretable, linearizing transforms for nonlinear PDEs. |
| Tasks | |
| Published | 2019-11-07 |
| URL | https://arxiv.org/abs/1911.02710v1 |
| https://arxiv.org/pdf/1911.02710v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-learning-models-for-global-coordinate |
| Repo | |
| Framework | |
Analysis of the fiber laydown quality in spunbond processes with simulation experiments evaluated by blocked neural networks
| Title | Analysis of the fiber laydown quality in spunbond processes with simulation experiments evaluated by blocked neural networks |
| Authors | Simone Gramsch, Alex Sarishvili, Andre Schmeißer |
| Abstract | We present a simulation framework for spunbond processes and use a design of experiments to investigate the cause-and-effect-relations of process and material parameters onto the fiber laydown on a conveyor belt. The virtual experiments are analyzed by a blocked neural network. This forms the basis for the prediction of the fiber laydown characteristics and enables a quick ranking of the significance of the influencing effects. We conclude our research by an analysis of the nonlinear cause-and-effect relations. |
| Tasks | |
| Published | 2019-11-14 |
| URL | https://arxiv.org/abs/1911.06213v2 |
| https://arxiv.org/pdf/1911.06213v2.pdf | |
| PWC | https://paperswithcode.com/paper/analysis-of-the-fiber-laydown-quality-in |
| Repo | |
| Framework | |
