Paper Group ANR 1526
Non-intrusive Load Monitoring via Multi-label Sparse Representation based Classification. Correlation Coefficients and Semantic Textual Similarity. DPPNet: Approximating Determinantal Point Processes with Deep Networks. ScienceExamCER: A High-Density Fine-Grained Science-Domain Corpus for Common Entity Recognition. DeepSFM: Structure From Motion Vi …
Non-intrusive Load Monitoring via Multi-label Sparse Representation based Classification
| Title | Non-intrusive Load Monitoring via Multi-label Sparse Representation based Classification |
| Authors | Shikha Singh, Angshul Majumdar |
| Abstract | This work follows the approach of multi-label classification for non-intrusive load monitoring (NILM). We modify the popular sparse representation based classification (SRC) approach (developed for single label classification) to solve multi-label classification problems. Results on benchmark REDD and Pecan Street dataset shows significant improvement over state-of-the-art techniques with small volume of training data. |
| Tasks | Multi-Label Classification, Non-Intrusive Load Monitoring, Sparse Representation-based Classification |
| Published | 2019-12-11 |
| URL | https://arxiv.org/abs/1912.07360v1 |
| https://arxiv.org/pdf/1912.07360v1.pdf | |
| PWC | https://paperswithcode.com/paper/non-intrusive-load-monitoring-via-multi-label |
| Repo | |
| Framework | |
Correlation Coefficients and Semantic Textual Similarity
| Title | Correlation Coefficients and Semantic Textual Similarity |
| Authors | Vitalii Zhelezniak, Aleksandar Savkov, April Shen, Nils Y. Hammerla |
| Abstract | A large body of research into semantic textual similarity has focused on constructing state-of-the-art embeddings using sophisticated modelling, careful choice of learning signals and many clever tricks. By contrast, little attention has been devoted to similarity measures between these embeddings, with cosine similarity being used unquestionably in the majority of cases. In this work, we illustrate that for all common word vectors, cosine similarity is essentially equivalent to the Pearson correlation coefficient, which provides some justification for its use. We thoroughly characterise cases where Pearson correlation (and thus cosine similarity) is unfit as similarity measure. Importantly, we show that Pearson correlation is appropriate for some word vectors but not others. When it is not appropriate, we illustrate how common non-parametric rank correlation coefficients can be used instead to significantly improve performance. We support our analysis with a series of evaluations on word-level and sentence-level semantic textual similarity benchmarks. On the latter, we show that even the simplest averaged word vectors compared by rank correlation easily rival the strongest deep representations compared by cosine similarity. |
| Tasks | Semantic Textual Similarity |
| Published | 2019-05-19 |
| URL | https://arxiv.org/abs/1905.07790v1 |
| https://arxiv.org/pdf/1905.07790v1.pdf | |
| PWC | https://paperswithcode.com/paper/correlation-coefficients-and-semantic-textual |
| Repo | |
| Framework | |
DPPNet: Approximating Determinantal Point Processes with Deep Networks
| Title | DPPNet: Approximating Determinantal Point Processes with Deep Networks |
| Authors | Zelda Mariet, Yaniv Ovadia, Jasper Snoek |
| Abstract | Determinantal Point Processes (DPPs) provide an elegant and versatile way to sample sets of items that balance the point-wise quality with the set-wise diversity of selected items. For this reason, they have gained prominence in many machine learning applications that rely on subset selection. However, sampling from a DPP over a ground set of size $N$ is a costly operation, requiring in general an $O(N^3)$ preprocessing cost and an $O(Nk^3)$ sampling cost for subsets of size $k$. We approach this problem by introducing DPPNets: generative deep models that produce DPP-like samples for arbitrary ground sets. We develop an inhibitive attention mechanism based on transformer networks that captures a notion of dissimilarity between feature vectors. We show theoretically that such an approximation is sensible as it maintains the guarantees of inhibition or dissimilarity that makes DPPs so powerful and unique. Empirically, we demonstrate that samples from our model receive high likelihood under the more expensive DPP alternative. |
| Tasks | Point Processes |
| Published | 2019-01-07 |
| URL | http://arxiv.org/abs/1901.02051v1 |
| http://arxiv.org/pdf/1901.02051v1.pdf | |
| PWC | https://paperswithcode.com/paper/dppnet-approximating-determinantal-point |
| Repo | |
| Framework | |
ScienceExamCER: A High-Density Fine-Grained Science-Domain Corpus for Common Entity Recognition
| Title | ScienceExamCER: A High-Density Fine-Grained Science-Domain Corpus for Common Entity Recognition |
| Authors | Hannah Smith, Zeyu Zhang, John Culnan, Peter Jansen |
| Abstract | Named entity recognition identifies common classes of entities in text, but these entity labels are generally sparse, limiting utility to downstream tasks. In this work we present ScienceExamCER, a densely-labeled semantic classification corpus of 133k mentions in the science exam domain where nearly all (96%) of content words have been annotated with one or more fine-grained semantic class labels including taxonomic groups, meronym groups, verb/action groups, properties and values, and synonyms. Semantic class labels are drawn from a manually-constructed fine-grained typology of 601 classes generated through a data-driven analysis of 4,239 science exam questions. We show an off-the-shelf BERT-based named entity recognition model modified for multi-label classification achieves an accuracy of 0.85 F1 on this task, suggesting strong utility for downstream tasks in science domain question answering requiring densely-labeled semantic classification. |
| Tasks | Multi-Label Classification, Named Entity Recognition, Question Answering |
| Published | 2019-11-24 |
| URL | https://arxiv.org/abs/1911.10436v1 |
| https://arxiv.org/pdf/1911.10436v1.pdf | |
| PWC | https://paperswithcode.com/paper/scienceexamcer-a-high-density-fine-grained |
| Repo | |
| Framework | |
DeepSFM: Structure From Motion Via Deep Bundle Adjustment
| Title | DeepSFM: Structure From Motion Via Deep Bundle Adjustment |
| Authors | Xingkui Wei, Yinda Zhang, Zhuwen Li, Yanwei Fu, Xiangyang Xue |
| Abstract | Structure from motion (SfM) is an essential computer vision problem which has not been well handled by deep learning. One of the promising trends is to apply explicit structural constraint, e.g. 3D cost volume, into the network.In this work, we design a physical driven architecture, namely DeepSFM, inspired by traditional Bundle Adjustment (BA), which consists of two cost volume based architectures for depth and pose estimation respectively, iteratively running to improve both.In each cost volume, we encode not only photo-metric consistency across multiple input images, but also geometric consistency to ensure that depths from multiple views agree with each other.The explicit constraints on both depth (structure) and pose (motion), when combined with the learning components, bring the merit from both traditional BA and emerging deep learning technology.Extensive experiments on various datasets show that our model achieves the state-of-the-art performance on both depth and pose estimation with superior robustness against less number of inputs and the noise in initialization. |
| Tasks | Pose Estimation |
| Published | 2019-12-20 |
| URL | https://arxiv.org/abs/1912.09697v1 |
| https://arxiv.org/pdf/1912.09697v1.pdf | |
| PWC | https://paperswithcode.com/paper/191209697 |
| Repo | |
| Framework | |
DLGAN: Disentangling Label-Specific Fine-Grained Features for Image Manipulation
| Title | DLGAN: Disentangling Label-Specific Fine-Grained Features for Image Manipulation |
| Authors | Guanqi Zhan, Yihao Zhao, Bingchan Zhao, Haoqi Yuan, Baoquan Chen, Hao Dong |
| Abstract | Several recent studies have shown how disentangling images into content and feature spaces can provide controllable image translation/manipulation. In this paper, we propose a framework to enable utilizing discrete multi-labels to control which features to be disentangled,i.e., disentangling label-specific fine-grained features for image manipulation (dubbed DLGAN). By mapping the discrete label-specific attribute features into a continuous prior distribution, we enable leveraging the advantages of both discrete labels and reference images to achieve image manipulation in a hybrid fashion. For example, given a face image dataset (e.g., CelebA) with multiple discrete fine-grained labels, we can learn to smoothly interpolate a face image between black hair and blond hair through reference images while immediately control the gender and age through discrete input labels. To the best of our knowledge, this is the first work to realize such a hybrid manipulation within a single model. Qualitative and quantitative experiments demonstrate the effectiveness of the proposed method |
| Tasks | |
| Published | 2019-11-22 |
| URL | https://arxiv.org/abs/1911.09943v1 |
| https://arxiv.org/pdf/1911.09943v1.pdf | |
| PWC | https://paperswithcode.com/paper/dlgan-disentangling-label-specific-fine |
| Repo | |
| Framework | |
What is the relationship between face alignment and facial expression recognition?
| Title | What is the relationship between face alignment and facial expression recognition? |
| Authors | Romain Belmonte, Benjamin Allaert, Pierre Tirilly, Ioan Marius Bilasco, Chaabane Djeraba, Nicu Sebe |
| Abstract | Face expression recognition is still a complex task, particularly due to the presence of head pose variations. Although face alignment approaches are becoming increasingly accurate for characterizing facial regions, it is important to consider the impact of these approaches when they are used for other related tasks such as head pose registration or facial expression recognition. In this paper, we compare the performance of recent face alignment approaches to highlight the most appropriate techniques for preserving facial geometry when correcting the head pose variation. Also, we highlight the most suitable techniques that locate facial landmarks in the presence of head pose variations and facial expressions. |
| Tasks | Face Alignment, Facial Expression Recognition |
| Published | 2019-05-26 |
| URL | https://arxiv.org/abs/1905.10784v1 |
| https://arxiv.org/pdf/1905.10784v1.pdf | |
| PWC | https://paperswithcode.com/paper/what-is-the-relationship-between-face |
| Repo | |
| Framework | |
Characterization of migrated seismic volumes using texture attributes: a comparative study
| Title | Characterization of migrated seismic volumes using texture attributes: a comparative study |
| Authors | Zhiling Long, Yazeed Alaudah, Muhammad Ali Qureshi, Motaz Al Farraj, Zhen Wang, Asjad Amin, Mohamed Deriche, Ghassan AlRegib |
| Abstract | In this paper, we examine several typical texture attributes developed in the image processing community in recent years with respect to their capability of characterizing a migrated seismic volume. These attributes are generated in either frequency or space domain, including steerable pyramid, curvelet, local binary pattern, and local radius index. The comparative study is performed within an image retrieval framework. We evaluate these attributes in terms of retrieval accuracy. It is our hope that this comparative study will help acquaint the seismic interpretation community with the many available powerful image texture analysis techniques, providing more alternative attributes for their seismic exploration. |
| Tasks | Image Retrieval, Seismic Interpretation, Texture Classification |
| Published | 2019-01-30 |
| URL | http://arxiv.org/abs/1901.10909v1 |
| http://arxiv.org/pdf/1901.10909v1.pdf | |
| PWC | https://paperswithcode.com/paper/characterization-of-migrated-seismic-volumes |
| Repo | |
| Framework | |
Unsupervised Learning-based Depth Estimation aided Visual SLAM Approach
| Title | Unsupervised Learning-based Depth Estimation aided Visual SLAM Approach |
| Authors | Mingyang Geng, Suning Shang, Bo Ding, Huaimin Wang, Pengfei Zhang, Lei Zhang |
| Abstract | The RGB-D camera maintains a limited range for working and is hard to accurately measure the depth information in a far distance. Besides, the RGB-D camera will easily be influenced by strong lighting and other external factors, which will lead to a poor accuracy on the acquired environmental depth information. Recently, deep learning technologies have achieved great success in the visual SLAM area, which can directly learn high-level features from the visual inputs and improve the estimation accuracy of the depth information. Therefore, deep learning technologies maintain the potential to extend the source of the depth information and improve the performance of the SLAM system. However, the existing deep learning-based methods are mainly supervised and require a large amount of ground-truth depth data, which is hard to acquire because of the realistic constraints. In this paper, we first present an unsupervised learning framework, which not only uses image reconstruction for supervising but also exploits the pose estimation method to enhance the supervised signal and add training constraints for the task of monocular depth and camera motion estimation. Furthermore, we successfully exploit our unsupervised learning framework to assist the traditional ORB-SLAM system when the initialization module of ORB-SLAM method could not match enough features. Qualitative and quantitative experiments have shown that our unsupervised learning framework performs the depth estimation task comparable to the supervised methods and outperforms the previous state-of-the-art approach by $13.5%$ on KITTI dataset. Besides, our unsupervised learning framework could significantly accelerate the initialization process of ORB-SLAM system and effectively improve the accuracy on environmental mapping in strong lighting and weak texture scenes. |
| Tasks | Depth And Camera Motion, Depth Estimation, Image Reconstruction, Motion Estimation, Pose Estimation |
| Published | 2019-01-22 |
| URL | http://arxiv.org/abs/1901.07288v1 |
| http://arxiv.org/pdf/1901.07288v1.pdf | |
| PWC | https://paperswithcode.com/paper/unsupervised-learning-based-depth-estimation |
| Repo | |
| Framework | |
Low-Rank Deep Convolutional Neural Network for Multi-Task Learning
| Title | Low-Rank Deep Convolutional Neural Network for Multi-Task Learning |
| Authors | Fang Su, Hai-Yang Shang, Jing-Yan Wang |
| Abstract | In this paper, we propose a novel multi-task learning method based on the deep convolutional network. The proposed deep network has four convolutional layers, three max-pooling layers, and two parallel fully connected layers. To adjust the deep network to multi-task learning problem, we propose to learn a low-rank deep network so that the relation among different tasks can be explored. We proposed to minimize the number of independent parameter rows of one fully connected layer to explore the relations among different tasks, which is measured by the nuclear norm of the parameter of one fully connected layer, and seek a low-rank parameter matrix. Meanwhile, we also propose to regularize another fully connected layer by sparsity penalty, so that the useful features learned by the lower layers can be selected. The learning problem is solved by an iterative algorithm based on gradient descent and back-propagation algorithms. The proposed algorithm is evaluated over benchmark data sets of multiple face attribute prediction, multi-task natural language processing, and joint economics index predictions. The evaluation results show the advantage of the low-rank deep CNN model over multi-task problems. |
| Tasks | Multi-Task Learning |
| Published | 2019-04-12 |
| URL | http://arxiv.org/abs/1904.07320v1 |
| http://arxiv.org/pdf/1904.07320v1.pdf | |
| PWC | https://paperswithcode.com/paper/low-rank-deep-convolutional-neural-network |
| Repo | |
| Framework | |
Best-scored Random Forest Density Estimation
| Title | Best-scored Random Forest Density Estimation |
| Authors | Hanyuan Hang, Hongwei Wen |
| Abstract | This paper presents a brand new nonparametric density estimation strategy named the best-scored random forest density estimation whose effectiveness is supported by both solid theoretical analysis and significant experimental performance. The terminology best-scored stands for selecting one density tree with the best estimation performance out of a certain number of purely random density tree candidates and we then name the selected one the best-scored random density tree. In this manner, the ensemble of these selected trees that is the best-scored random density forest can achieve even better estimation results than simply integrating trees without selection. From the theoretical perspective, by decomposing the error term into two, we are able to carry out the following analysis: First of all, we establish the consistency of the best-scored random density trees under $L_1$-norm. Secondly, we provide the convergence rates of them under $L_1$-norm concerning with three different tail assumptions, respectively. Thirdly, the convergence rates under $L_{\infty}$-norm is presented. Last but not least, we also achieve the above convergence rates analysis for the best-scored random density forest. When conducting comparative experiments with other state-of-the-art density estimation approaches on both synthetic and real data sets, it turns out that our algorithm has not only significant advantages in terms of estimation accuracy over other methods, but also stronger resistance to the curse of dimensionality. |
| Tasks | Density Estimation |
| Published | 2019-05-09 |
| URL | https://arxiv.org/abs/1905.03729v1 |
| https://arxiv.org/pdf/1905.03729v1.pdf | |
| PWC | https://paperswithcode.com/paper/190503729 |
| Repo | |
| Framework | |
Implicit Rugosity Regularization via Data Augmentation
| Title | Implicit Rugosity Regularization via Data Augmentation |
| Authors | Daniel LeJeune, Randall Balestriero, Hamid Javadi, Richard G. Baraniuk |
| Abstract | Deep (neural) networks have been applied productively in a wide range of supervised and unsupervised learning tasks. Unlike classical machine learning algorithms, deep networks typically operate in the \emph{overparameterized} regime, where the number of parameters is larger than the number of training data points. Consequently, understanding the generalization properties and the role of (explicit or implicit) regularization in these networks is of great importance. In this work, we explore how the oft-used heuristic of \emph{data augmentation} imposes an {\em implicit regularization} penalty of a novel measure of the \emph{rugosity} or “roughness” based on the tangent Hessian of the function fit to the training data. |
| Tasks | Data Augmentation |
| Published | 2019-05-28 |
| URL | https://arxiv.org/abs/1905.11639v3 |
| https://arxiv.org/pdf/1905.11639v3.pdf | |
| PWC | https://paperswithcode.com/paper/a-hessian-based-complexity-measure-for-deep |
| Repo | |
| Framework | |
Admiring the Great Mountain: A Celebration Special Issue in Honor of Stephen Grossbergs 80th Birthday
| Title | Admiring the Great Mountain: A Celebration Special Issue in Honor of Stephen Grossbergs 80th Birthday |
| Authors | Donald C. Wunsch |
| Abstract | This editorial summarizes selected key contributions of Prof. Stephen Grossberg and describes the papers in this 80th birthday special issue in his honor. His productivity, creativity, and vision would each be enough to mark a scientist of the first caliber. In combination, they have resulted in contributions that have changed the entire discipline of neural networks. Grossberg has been tremendously influential in engineering, dynamical systems, and artificial intelligence as well. Indeed, he has been one of the most important mentors and role models in my career, and has done so with extraordinary generosity and encouragement. All authors in this special issue have taken great pleasure in hereby commemorating his extraordinary career and contributions. |
| Tasks | |
| Published | 2019-09-26 |
| URL | https://arxiv.org/abs/1910.13351v1 |
| https://arxiv.org/pdf/1910.13351v1.pdf | |
| PWC | https://paperswithcode.com/paper/admiring-the-great-mountain-a-celebration |
| Repo | |
| Framework | |
Spectral Multi-scale Community Detection in Temporal Networks with an Application
| Title | Spectral Multi-scale Community Detection in Temporal Networks with an Application |
| Authors | Zhana Kuncheva, Giovanni Montana |
| Abstract | The analysis of temporal networks has a wide area of applications in a world of technological advances. An important aspect of temporal network analysis is the discovery of community structures. Real data networks are often very large and the communities are observed to have a hierarchical structure referred to as multi-scale communities. Changes in the community structure over time might take place either at one scale or across all scales of the community structure. The multilayer formulation of the modularity maximization (MM) method introduced captures the changing multi-scale community structure of temporal networks. This method introduces a coupling between communities in neighboring time layers by allowing inter-layer connections, while different values of the resolution parameter enable the detection of multi-scale communities. However, the range of this parameter’s values must be manually selected. When dealing with real life data, communities at one or more scales can go undiscovered if appropriate parameter ranges are not selected. A novel Temporal Multi-scale Community Detection (TMSCD) method overcomes the obstacles mentioned above. This is achieved by using the spectral properties of the temporal network represented as a multilayer network. In this framework we select automatically the range of relevant scales within which multi-scale community partitions are sought. |
| Tasks | Community Detection |
| Published | 2019-01-29 |
| URL | http://arxiv.org/abs/1901.10521v1 |
| http://arxiv.org/pdf/1901.10521v1.pdf | |
| PWC | https://paperswithcode.com/paper/spectral-multi-scale-community-detection-in |
| Repo | |
| Framework | |
Abstraction for Zooming-In to Unsolvability Reasons of Grid-Cell Problems
| Title | Abstraction for Zooming-In to Unsolvability Reasons of Grid-Cell Problems |
| Authors | Thomas Eiter, Zeynep G. Saribatur, Peter Schüller |
| Abstract | Humans are capable of abstracting away irrelevant details when studying problems. This is especially noticeable for problems over grid-cells, as humans are able to disregard certain parts of the grid and focus on the key elements important for the problem. Recently, the notion of abstraction has been introduced for Answer Set Programming (ASP), a knowledge representation and reasoning paradigm widely used in problem solving, with the potential to understand the key elements of a program that play a role in finding a solution. The present paper takes this further and empowers abstraction to deal with structural aspects, and in particular with hierarchical abstraction over the domain. We focus on obtaining the reasons for unsolvability of problems on grids, and show the possibility to automatically achieve human-like abstractions that distinguish only the relevant part of the grid. A user study on abstract explanations confirms the similarity of the focus points in machine vs. human explanations and reaffirms the challenge of employing abstraction to obtain machine explanations. |
| Tasks | |
| Published | 2019-09-11 |
| URL | https://arxiv.org/abs/1909.04998v1 |
| https://arxiv.org/pdf/1909.04998v1.pdf | |
| PWC | https://paperswithcode.com/paper/abstraction-for-zooming-in-to-unsolvability |
| Repo | |
| Framework | |
