Paper Group ANR 482
Multivariate, Multistep Forecasting, Reconstruction and Feature Selection of Ocean Waves via Recurrent and Sequence-to-Sequence Networks. Metric Classification Network in Actual Face Recognition Scene. Unknown Identity Rejection Loss: Utilizing Unlabeled Data for Face Recognition. On Multi-Cause Causal Inference with Unobserved Confounding: Counter …
Multivariate, Multistep Forecasting, Reconstruction and Feature Selection of Ocean Waves via Recurrent and Sequence-to-Sequence Networks
| Title | Multivariate, Multistep Forecasting, Reconstruction and Feature Selection of Ocean Waves via Recurrent and Sequence-to-Sequence Networks |
| Authors | Mohammad Pirhooshyaran, Lawrence V. Snyder |
| Abstract | This article explores the concepts of ocean wave multivariate multistep forecasting, reconstruction and feature selection. We introduce recurrent neural network frameworks, integrated with Bayesian hyperparameter optimization and Elastic Net methods. We consider both short- and long-term forecasts and reconstruction, for significant wave height and output power of the ocean waves. Sequence-to-sequence neural networks are being developed for the first time to reconstruct the missing characteristics of ocean waves based on information from nearby wave sensors. Our results indicate that the Adam and AMSGrad optimization algorithms are the most robust ones to optimize the sequence-to-sequence network. For the case of significant wave height reconstruction, we compare the proposed methods with alternatives on a well-studied dataset. We show the superiority of the proposed methods considering several error metrics. We design a new case study based on measurement stations along the east coast of the United States and investigate the feature selection concept. Comparisons substantiate the benefit of utilizing Elastic Net. Moreover, case study results indicate that when the number of features is considerable, having deeper structures improves the performance. |
| Tasks | Feature Selection, Hyperparameter Optimization |
| Published | 2019-06-01 |
| URL | https://arxiv.org/abs/1906.00195v2 |
| https://arxiv.org/pdf/1906.00195v2.pdf | |
| PWC | https://paperswithcode.com/paper/190600195 |
| Repo | |
| Framework | |
Metric Classification Network in Actual Face Recognition Scene
| Title | Metric Classification Network in Actual Face Recognition Scene |
| Authors | Jian Li, Yan Wang, Xiubao Zhang, Weihong Deng, Haifeng Shen |
| Abstract | In order to make facial features more discriminative, some new models have recently been proposed. However, almost all of these models use the traditional face verification method, where the cosine operation is performed using the features of the bottleneck layer output. However, each of these models needs to change a threshold each time it is operated on a different test set. This is very inappropriate for application in real-world scenarios. In this paper, we train a validation classifier to normalize the decision threshold, which means that the result can be obtained directly without replacing the threshold. We refer to our model as validation classifier, which achieves best result on the structure consisting of one convolution layer and six fully connected layers. To test our approach, we conduct extensive experiments on Labeled Face in the Wild (LFW) and Youtube Faces (YTF), and the relative error reduction is 25.37% and 26.60% than traditional method respectively. These experiments confirm the effectiveness of validation classifier on face recognition task. |
| Tasks | Face Recognition, Face Verification |
| Published | 2019-10-25 |
| URL | https://arxiv.org/abs/1910.11563v1 |
| https://arxiv.org/pdf/1910.11563v1.pdf | |
| PWC | https://paperswithcode.com/paper/metric-classification-network-in-actual-face |
| Repo | |
| Framework | |
Unknown Identity Rejection Loss: Utilizing Unlabeled Data for Face Recognition
| Title | Unknown Identity Rejection Loss: Utilizing Unlabeled Data for Face Recognition |
| Authors | Haiming Yu, Yin Fan, Keyu Chen, He Yan, Xiangju Lu, Junhui Liu, Danming Xie |
| Abstract | Face recognition has advanced considerably with the availability of large-scale labeled datasets. However, how to further improve the performance with the easily accessible unlabeled dataset remains a challenge. In this paper, we propose the novel Unknown Identity Rejection (UIR) loss to utilize the unlabeled data. We categorize identities in unconstrained environment into the known set and the unknown set. The former corresponds to the identities that appear in the labeled training dataset while the latter is its complementary set. Besides training the model to accurately classify the known identities, we also force the model to reject unknown identities provided by the unlabeled dataset via our proposed UIR loss. In order to ‘reject’ faces of unknown identities, centers of the known identities are forced to keep enough margin from centers of unknown identities which are assumed to be approximated by the features of their samples. By this means, the discriminativeness of the face representations can be enhanced. Experimental results demonstrate that our approach can provide obvious performance improvement by utilizing the unlabeled data. |
| Tasks | Face Recognition |
| Published | 2019-10-24 |
| URL | https://arxiv.org/abs/1910.10896v1 |
| https://arxiv.org/pdf/1910.10896v1.pdf | |
| PWC | https://paperswithcode.com/paper/unknown-identity-rejection-loss-utilizing |
| Repo | |
| Framework | |
On Multi-Cause Causal Inference with Unobserved Confounding: Counterexamples, Impossibility, and Alternatives
| Title | On Multi-Cause Causal Inference with Unobserved Confounding: Counterexamples, Impossibility, and Alternatives |
| Authors | Alexander D’Amour |
| Abstract | Unobserved confounding is a central barrier to drawing causal inferences from observational data. Several authors have recently proposed that this barrier can be overcome in the case where one attempts to infer the effects of several variables simultaneously. In this paper, we present two simple, analytical counterexamples that challenge the general claims that are central to these approaches. In addition, we show that nonparametric identification is impossible in this setting. We discuss practical implications, and suggest alternatives to the methods that have been proposed so far in this line of work: using proxy variables and shifting focus to sensitivity analysis. |
| Tasks | Causal Inference |
| Published | 2019-02-27 |
| URL | http://arxiv.org/abs/1902.10286v4 |
| http://arxiv.org/pdf/1902.10286v4.pdf | |
| PWC | https://paperswithcode.com/paper/on-multi-cause-causal-inference-with |
| Repo | |
| Framework | |
Boosting Mapping Functionality of Neural Networks via Latent Feature Generation based on Reversible Learning
| Title | Boosting Mapping Functionality of Neural Networks via Latent Feature Generation based on Reversible Learning |
| Authors | Jongmin Yu |
| Abstract | This paper addresses a boosting method for mapping functionality of neural networks in visual recognition such as image classification and face recognition. We present reversible learning for generating and learning latent features using the network itself. By generating latent features corresponding to hard samples and applying the generated features in a training stage, reversible learning can improve a mapping functionality without additional data augmentation or handling the bias of dataset. We demonstrate an efficiency of the proposed method on the MNIST,Cifar-10/100, and Extremely Biased and poorly categorized dataset (EBPC dataset). The experimental results show that the proposed method can outperform existing state-of-the-art methods in visual recognition. Extensive analysis shows that our method can efficiently improve the mapping capability of a network. |
| Tasks | Data Augmentation, Face Recognition, Image Classification |
| Published | 2019-10-21 |
| URL | https://arxiv.org/abs/1910.09108v1 |
| https://arxiv.org/pdf/1910.09108v1.pdf | |
| PWC | https://paperswithcode.com/paper/boosting-mapping-functionality-of-neural |
| Repo | |
| Framework | |
Boosting Network Weight Separability via Feed-Backward Reconstruction
| Title | Boosting Network Weight Separability via Feed-Backward Reconstruction |
| Authors | Jongmin Yu, Younkwan Lee, Moongu Jeon |
| Abstract | This paper proposes a new evaluation metric and boosting method for weight separability in neural network design. In contrast to general visual recognition methods designed to encourage both intra-class compactness and inter-class separability of latent features, we focus on estimating linear independence of column vectors in weight matrix and improving the separability of weight vectors. To this end, we propose an evaluation metric for weight separability based on semi-orthogonality of a matrix and Frobenius distance, and the feed-backward reconstruction loss which explicitly encourages weight separability between the column vectors in the weight matrix. The experimental results on image classification and face recognition demonstrate that the weight separability boosting via minimization of feed-backward reconstruction loss can improve the visual recognition performance, hence universally boosting the performance on various visual recognition tasks. |
| Tasks | Face Recognition, Image Classification |
| Published | 2019-10-20 |
| URL | https://arxiv.org/abs/1910.09024v1 |
| https://arxiv.org/pdf/1910.09024v1.pdf | |
| PWC | https://paperswithcode.com/paper/boosting-network-weight-separability-via-feed |
| Repo | |
| Framework | |
On adversarial patches: real-world attack on ArcFace-100 face recognition system
| Title | On adversarial patches: real-world attack on ArcFace-100 face recognition system |
| Authors | Mikhail Pautov, Grigorii Melnikov, Edgar Kaziakhmedov, Klim Kireev, Aleksandr Petiushko |
| Abstract | Recent works showed the vulnerability of image classifiers to adversarial attacks in the digital domain. However, the majority of attacks involve adding small perturbation to an image to fool the classifier. Unfortunately, such procedures can not be used to conduct a real-world attack, where adding an adversarial attribute to the photo is a more practical approach. In this paper, we study the problem of real-world attacks on face recognition systems. We examine security of one of the best public face recognition systems, LResNet100E-IR with ArcFace loss, and propose a simple method to attack it in the physical world. The method suggests creating an adversarial patch that can be printed, added as a face attribute and photographed; the photo of a person with such attribute is then passed to the classifier such that the classifier’s recognized class changes from correct to the desired one. Proposed generating procedure allows projecting adversarial patches not only on different areas of the face, such as nose or forehead but also on some wearable accessory, such as eyeglasses. |
| Tasks | Face Recognition |
| Published | 2019-10-15 |
| URL | https://arxiv.org/abs/1910.07067v2 |
| https://arxiv.org/pdf/1910.07067v2.pdf | |
| PWC | https://paperswithcode.com/paper/on-adversarial-patches-real-world-attack-on |
| Repo | |
| Framework | |
Classifying Treatment Responders Under Causal Effect Monotonicity
| Title | Classifying Treatment Responders Under Causal Effect Monotonicity |
| Authors | Nathan Kallus |
| Abstract | In the context of individual-level causal inference, we study the problem of predicting whether someone will respond or not to a treatment based on their features and past examples of features, treatment indicator (e.g., drug/no drug), and a binary outcome (e.g., recovery from disease). As a classification task, the problem is made difficult by not knowing the example outcomes under the opposite treatment indicators. We assume the effect is monotonic, as in advertising’s effect on a purchase or bail-setting’s effect on reappearance in court: either it would have happened regardless of treatment, not happened regardless, or happened only depending on exposure to treatment. Predicting whether the latter is latently the case is our focus. While previous work focuses on conditional average treatment effect estimation, formulating the problem as a classification task rather than an estimation task allows us to develop new tools more suited to this problem. By leveraging monotonicity, we develop new discriminative and generative algorithms for the responder-classification problem. We explore and discuss connections to corrupted data and policy learning. We provide an empirical study with both synthetic and real datasets to compare these specialized algorithms to standard benchmarks. |
| Tasks | Causal Inference |
| Published | 2019-02-14 |
| URL | https://arxiv.org/abs/1902.05482v2 |
| https://arxiv.org/pdf/1902.05482v2.pdf | |
| PWC | https://paperswithcode.com/paper/classifying-treatment-responders-under-causal |
| Repo | |
| Framework | |
Causal Effect Identification from Multiple Incomplete Data Sources: A General Search-based Approach
| Title | Causal Effect Identification from Multiple Incomplete Data Sources: A General Search-based Approach |
| Authors | Santtu Tikka, Antti Hyttinen, Juha Karvanen |
| Abstract | Causal effect identification considers whether an interventional probability distribution can be uniquely determined without parametric assumptions from measured source distributions and structural knowledge on the generating system. While complete graphical criteria and procedures exist for many identification problems, there are still challenging but important extensions that have not been considered in the literature. To tackle these new settings, we present a search algorithm directly over the rules of do-calculus. Due to generality of do-calculus, the search is capable of taking more advanced data-generating mechanisms into account along with an arbitrary type of both observational and experimental source distributions. The search is enhanced via a heuristic and search space reduction techniques. The approach, called do-search, is provably sound, and it is complete with respect to identifiability problems that have been shown to be completely characterized by do-calculus. When extended with additional rules, the search is capable of handling missing data problems as well. With the versatile search, we are able to approach new problems such as combined transportability and selection bias, or multiple sources of selection bias. We perform a systematic analysis of bivariate missing data problems and study causal inference under case-control design. We also present the R package dosearch that provides an interface for a C++ implementation of the search. |
| Tasks | Causal Inference |
| Published | 2019-02-04 |
| URL | https://arxiv.org/abs/1902.01073v3 |
| https://arxiv.org/pdf/1902.01073v3.pdf | |
| PWC | https://paperswithcode.com/paper/causal-effect-identification-from-multiple |
| Repo | |
| Framework | |
SQuAP-Ont: an Ontology of Software Quality Relational Factors from Financial Systems
| Title | SQuAP-Ont: an Ontology of Software Quality Relational Factors from Financial Systems |
| Authors | Paolo Ciancarini, Andrea Giovanni Nuzzolese, Valentina Presutti, Daniel Russo |
| Abstract | Quality, architecture, and process are considered the keystones of software engineering. ISO defines them in three separate standards. However, their interaction has been scarcely studied, so far. The SQuAP model (Software Quality, Architecture, Process) describes twenty-eight main factors that impact on software quality in banking systems, and each factor is described as a relation among some characteristics from the three ISO standards. Hence, SQuAP makes such relations emerge rigorously, although informally. In this paper, we present SQuAP-Ont, an OWL ontology designed by following a well-established methodology based on the re-use of Ontology Design Patterns (i.e. ODPs). SQuAP-Ont formalises the relations emerging from SQuAP to represent and reason via Linked Data about software engineering in a three-dimensional model consisting of quality, architecture, and process ISO characteristics. |
| Tasks | |
| Published | 2019-09-04 |
| URL | https://arxiv.org/abs/1909.01602v1 |
| https://arxiv.org/pdf/1909.01602v1.pdf | |
| PWC | https://paperswithcode.com/paper/squap-ont-an-ontology-of-software-quality |
| Repo | |
| Framework | |
Comprehensive Analysis of Dynamic Message Sign Impact on Driver Behavior: A Random Forest Approach
| Title | Comprehensive Analysis of Dynamic Message Sign Impact on Driver Behavior: A Random Forest Approach |
| Authors | Snehanshu Banerjee, Mansoureh Jeihani, Danny D. Brown, Samira Ahangari |
| Abstract | This study investigates the potential effects of different Dynamic Message Signs (DMSs) on driver behavior using a full-scale high-fidelity driving simulator. Different DMSs are categorized by their content, structure, and type of messages. A random forest algorithm is used for three separate behavioral analyses; a route diversion analysis, a route choice analysis and a compliance analysis; to identify the potential and relative influences of different DMSs on these aspects of driver behavior. A total of 390 simulation runs are conducted using a sample of 65 participants from diverse socioeconomic backgrounds. Results obtained suggest that DMSs displaying lane closure and delay information with advisory messages are most influential with regards to diversion while color-coded DMSs and DMSs with avoid route advice are the top contributors impacting route choice decisions and DMS compliance. In this first-of-a-kind study, based on the responses to the pre and post simulation surveys as well as results obtained from the analysis of driving-simulation-session data, the authors found that color-blind-friendly, color-coded DMSs are more effective than alphanumeric DMSs - especially in scenarios that demand high compliance from drivers. The increased effectiveness may be attributed to reduced comprehension time and ease with which such DMSs are understood by a greater percentage of road users. |
| Tasks | |
| Published | 2019-03-10 |
| URL | http://arxiv.org/abs/1903.12070v1 |
| http://arxiv.org/pdf/1903.12070v1.pdf | |
| PWC | https://paperswithcode.com/paper/comprehensive-analysis-of-dynamic-message |
| Repo | |
| Framework | |
Multimodal Fusion with Deep Neural Networks for Audio-Video Emotion Recognition
| Title | Multimodal Fusion with Deep Neural Networks for Audio-Video Emotion Recognition |
| Authors | Juan D. S. Ortega, Mohammed Senoussaoui, Eric Granger, Marco Pedersoli, Patrick Cardinal, Alessandro L. Koerich |
| Abstract | This paper presents a novel deep neural network (DNN) for multimodal fusion of audio, video and text modalities for emotion recognition. The proposed DNN architecture has independent and shared layers which aim to learn the representation for each modality, as well as the best combined representation to achieve the best prediction. Experimental results on the AVEC Sentiment Analysis in the Wild dataset indicate that the proposed DNN can achieve a higher level of Concordance Correlation Coefficient (CCC) than other state-of-the-art systems that perform early fusion of modalities at feature-level (i.e., concatenation) and late fusion at score-level (i.e., weighted average) fusion. The proposed DNN has achieved CCCs of 0.606, 0.534, and 0.170 on the development partition of the dataset for predicting arousal, valence and liking, respectively. |
| Tasks | Emotion Recognition, Sentiment Analysis, Video Emotion Recognition |
| Published | 2019-07-06 |
| URL | https://arxiv.org/abs/1907.03196v1 |
| https://arxiv.org/pdf/1907.03196v1.pdf | |
| PWC | https://paperswithcode.com/paper/multimodal-fusion-with-deep-neural-networks |
| Repo | |
| Framework | |
Detecting intracranial aneurysm rupture from 3D surfaces using a novel GraphNet approach
| Title | Detecting intracranial aneurysm rupture from 3D surfaces using a novel GraphNet approach |
| Authors | Z. Ma, L. Song, X. Feng, G. Yang, W. Zhu, J. Liu, Y. Zhang, X. Yang, Y. Yin |
| Abstract | Intracranial aneurysm (IA) is a life-threatening blood spot in human’s brain if it ruptures and causes cerebral hemorrhage. It is challenging to detect whether an IA has ruptured from medical images. In this paper, we propose a novel graph based neural network named GraphNet to detect IA rupture from 3D surface data. GraphNet is based on graph convolution network (GCN) and is designed for graph-level classification and node-level segmentation. The network uses GCN blocks to extract surface local features and pools to global features. 1250 patient data including 385 ruptured and 865 unruptured IAs were collected from clinic for experiments. The performance on randomly selected 234 test patient data was reported. The experiment with the proposed GraphNet achieved accuracy of 0.82, area-under-curve (AUC) of receiver operating characteristic (ROC) curve 0.82 in the classification task, significantly outperforming the baseline approach without using graph based networks. The segmentation output of the model achieved mean graph-node-based dice coefficient (DSC) score 0.88. |
| Tasks | |
| Published | 2019-10-17 |
| URL | https://arxiv.org/abs/1910.08375v1 |
| https://arxiv.org/pdf/1910.08375v1.pdf | |
| PWC | https://paperswithcode.com/paper/detecting-intracranial-aneurysm-rupture-from |
| Repo | |
| Framework | |
Low-rank Tensor Grid for Image Completion
| Title | Low-rank Tensor Grid for Image Completion |
| Authors | Huyan Huang, Yipeng Liu, Ce Zhu |
| Abstract | Tensor completion estimates missing components by exploiting the low-rank structure of multi-way data. The recently proposed methods based on tensor train (TT) and tensor ring (TR) show better performance in image recovery than classical ones. Compared with TT and TR, the projected entangled pair state (PEPS), which is also called tensor grid (TG), allows more interactions between different dimensions, and may lead to more compact representation. In this paper, we propose to perform image completion based on low-rank tensor grid. A two-stage density matrix renormalization group algorithm is used for initialization of TG decomposition, which consists of multiple TT decompositions. The latent TG factors can be alternatively obtained by solving alternating least squares problems. To further improve the computational efficiency, a multi-linear matrix factorization for low rank TG completion is developed by using parallel matrix factorization. Experimental results on synthetic data and real-world images show the proposed methods outperform the existing ones in terms of recovery accuracy. |
| Tasks | |
| Published | 2019-03-12 |
| URL | https://arxiv.org/abs/1903.04735v2 |
| https://arxiv.org/pdf/1903.04735v2.pdf | |
| PWC | https://paperswithcode.com/paper/tensor-grid-decomposition-with-application-to |
| Repo | |
| Framework | |
Weight-space symmetry in deep networks gives rise to permutation saddles, connected by equal-loss valleys across the loss landscape
| Title | Weight-space symmetry in deep networks gives rise to permutation saddles, connected by equal-loss valleys across the loss landscape |
| Authors | Johanni Brea, Berfin Simsek, Bernd Illing, Wulfram Gerstner |
| Abstract | The permutation symmetry of neurons in each layer of a deep neural network gives rise not only to multiple equivalent global minima of the loss function, but also to first-order saddle points located on the path between the global minima. In a network of $d-1$ hidden layers with $n_k$ neurons in layers $k = 1, \ldots, d$, we construct smooth paths between equivalent global minima that lead through a permutation point' where the input and output weight vectors of two neurons in the same hidden layer $k$ collide and interchange. We show that such permutation points are critical points with at least $n_{k+1}$ vanishing eigenvalues of the Hessian matrix of second derivatives indicating a local plateau of the loss function. We find that a permutation point for the exchange of neurons $i$ and $j$ transits into a flat valley (or generally, an extended plateau of $n_{k+1}$ flat dimensions) that enables all $n_k!$ permutations of neurons in a given layer $k$ at the same loss value. Moreover, we introduce high-order permutation points by exploiting the recursive structure in neural network functions, and find that the number of $K^{\text{th}}$-order permutation points is at least by a factor $\sum_{k=1}^{d-1}\frac{1}{2!^K}{n_k-K \choose K}$ larger than the (already huge) number of equivalent global minima. In two tasks, we illustrate numerically that some of the permutation points correspond to first-order saddles (permutation saddles’): first, in a toy network with a single hidden layer on a function approximation task and, second, in a multilayer network on the MNIST task. Our geometric approach yields a lower bound on the number of critical points generated by weight-space symmetries and provides a simple intuitive link between previous mathematical results and numerical observations. |
| Tasks | |
| Published | 2019-07-05 |
| URL | https://arxiv.org/abs/1907.02911v1 |
| https://arxiv.org/pdf/1907.02911v1.pdf | |
| PWC | https://paperswithcode.com/paper/weight-space-symmetry-in-deep-networks-gives |
| Repo | |
| Framework | |
