Paper Group ANR 63
Data Augmentation in Emotion Classification Using Generative Adversarial Networks. All that is English may be Hindi: Enhancing language identification through automatic ranking of likeliness of word borrowing in social media. On Principal Components Regression, Random Projections, and Column Subsampling. Motion-Appearance Interactive Encoding for O …
Data Augmentation in Emotion Classification Using Generative Adversarial Networks
| Title | Data Augmentation in Emotion Classification Using Generative Adversarial Networks |
| Authors | Xinyue Zhu, Yifan Liu, Zengchang Qin, Jiahong Li |
| Abstract | It is a difficult task to classify images with multiple class labels using only a small number of labeled examples, especially when the label (class) distribution is imbalanced. Emotion classification is such an example of imbalanced label distribution, because some classes of emotions like \emph{disgusted} are relatively rare comparing to other labels like {\it happy or sad}. In this paper, we propose a data augmentation method using generative adversarial networks (GAN). It can complement and complete the data manifold and find better margins between neighboring classes. Specifically, we design a framework with a CNN model as the classifier and a cycle-consistent adversarial networks (CycleGAN) as the generator. In order to avoid gradient vanishing problem, we employ the least-squared loss as adversarial loss. We also propose several evaluation methods on three benchmark datasets to validate GAN’s performance. Empirical results show that we can obtain 5%~10% increase in the classification accuracy after employing the GAN-based data augmentation techniques. |
| Tasks | Data Augmentation, Emotion Classification |
| Published | 2017-11-02 |
| URL | http://arxiv.org/abs/1711.00648v5 |
| http://arxiv.org/pdf/1711.00648v5.pdf | |
| PWC | https://paperswithcode.com/paper/data-augmentation-in-emotion-classification |
| Repo | |
| Framework | |
All that is English may be Hindi: Enhancing language identification through automatic ranking of likeliness of word borrowing in social media
| Title | All that is English may be Hindi: Enhancing language identification through automatic ranking of likeliness of word borrowing in social media |
| Authors | Jasabanta Patro, Bidisha Samanta, Saurabh Singh, Abhipsa Basu, Prithwish Mukherjee, Monojit Choudhury, Animesh Mukherjee |
| Abstract | In this paper, we present a set of computational methods to identify the likeliness of a word being borrowed, based on the signals from social media. In terms of Spearman correlation coefficient values, our methods perform more than two times better (nearly 0.62) in predicting the borrowing likeliness compared to the best performing baseline (nearly 0.26) reported in literature. Based on this likeliness estimate we asked annotators to re-annotate the language tags of foreign words in predominantly native contexts. In 88 percent of cases the annotators felt that the foreign language tag should be replaced by native language tag, thus indicating a huge scope for improvement of automatic language identification systems. |
| Tasks | Language Identification |
| Published | 2017-07-25 |
| URL | http://arxiv.org/abs/1707.08446v2 |
| http://arxiv.org/pdf/1707.08446v2.pdf | |
| PWC | https://paperswithcode.com/paper/all-that-is-english-may-be-hindi-enhancing |
| Repo | |
| Framework | |
On Principal Components Regression, Random Projections, and Column Subsampling
| Title | On Principal Components Regression, Random Projections, and Column Subsampling |
| Authors | Martin Slawski |
| Abstract | Principal Components Regression (PCR) is a traditional tool for dimension reduction in linear regression that has been both criticized and defended. One concern about PCR is that obtaining the leading principal components tends to be computationally demanding for large data sets. While random projections do not possess the optimality properties of the leading principal subspace, they are computationally appealing and hence have become increasingly popular in recent years. In this paper, we present an analysis showing that for random projections satisfying a Johnson-Lindenstrauss embedding property, the prediction error in subsequent regression is close to that of PCR, at the expense of requiring a slightly large number of random projections than principal components. Column sub-sampling constitutes an even cheaper way of randomized dimension reduction outside the class of Johnson-Lindenstrauss transforms. We provide numerical results based on synthetic and real data as well as basic theory revealing differences and commonalities in terms of statistical performance. |
| Tasks | Dimensionality Reduction |
| Published | 2017-09-23 |
| URL | http://arxiv.org/abs/1709.08104v2 |
| http://arxiv.org/pdf/1709.08104v2.pdf | |
| PWC | https://paperswithcode.com/paper/on-principal-components-regression-random |
| Repo | |
| Framework | |
Motion-Appearance Interactive Encoding for Object Segmentation in Unconstrained Videos
| Title | Motion-Appearance Interactive Encoding for Object Segmentation in Unconstrained Videos |
| Authors | Chunchao Guo, Jianhuang Lai, Xiaohua Xie |
| Abstract | We present a novel method of integrating motion and appearance cues for foreground object segmentation in unconstrained videos. Unlike conventional methods encoding motion and appearance patterns individually, our method puts particular emphasis on their mutual assistance. Specifically, we propose using an interactively constrained encoding (ICE) scheme to incorporate motion and appearance patterns into a graph that leads to a spatiotemporal energy optimization. The reason of utilizing ICE is that both motion and appearance cues for the same target share underlying correlative structure, thus can be exploited in a deeply collaborative manner. We perform ICE not only in the initialization but also in the refinement stage of a two-layer framework for object segmentation. This scheme allows our method to consistently capture structural patterns about object perceptions throughout the whole framework. Our method can be operated on superpixels instead of raw pixels to reduce the number of graph nodes by two orders of magnitude. Moreover, we propose to partially explore the multi-object localization problem with inter-occlusion by weighted bipartite graph matching. Comprehensive experiments on three benchmark datasets (i.e., SegTrack, MOViCS, and GaTech) demonstrate the effectiveness of our approach compared with extensive state-of-the-art methods. |
| Tasks | Graph Matching, Object Localization, Semantic Segmentation |
| Published | 2017-07-25 |
| URL | http://arxiv.org/abs/1707.07857v1 |
| http://arxiv.org/pdf/1707.07857v1.pdf | |
| PWC | https://paperswithcode.com/paper/motion-appearance-interactive-encoding-for |
| Repo | |
| Framework | |
Deep Feature Learning via Structured Graph Laplacian Embedding for Person Re-Identification
| Title | Deep Feature Learning via Structured Graph Laplacian Embedding for Person Re-Identification |
| Authors | De Cheng, Yihong Gong, Zhihui Li, Weiwei Shi, Alexander G. Hauptmann, Nanning Zheng |
| Abstract | Learning the distance metric between pairs of examples is of great importance for visual recognition, especially for person re-identification (Re-Id). Recently, the contrastive and triplet loss are proposed to enhance the discriminative power of the deeply learned features, and have achieved remarkable success. As can be seen, either the contrastive or triplet loss is just one special case of the Euclidean distance relationships among these training samples. Therefore, we propose a structured graph Laplacian embedding algorithm, which can formulate all these structured distance relationships into the graph Laplacian form. The proposed method can take full advantages of the structured distance relationships among these training samples, with the constructed complete graph. Besides, this formulation makes our method easy-to-implement and super-effective. When embedding the proposed algorithm with the softmax loss for the CNN training, our method can obtain much more robust and discriminative deep features with inter-personal dispersion and intra-personal compactness, which is essential to person Re-Id. We illustrate the effectiveness of our proposed method on top of three popular networks, namely AlexNet, DGDNet and ResNet50, on recent four widely used Re-Id benchmark datasets. Our proposed method achieves state-of-the-art performances. |
| Tasks | Person Re-Identification |
| Published | 2017-07-25 |
| URL | http://arxiv.org/abs/1707.07791v1 |
| http://arxiv.org/pdf/1707.07791v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-feature-learning-via-structured-graph |
| Repo | |
| Framework | |
Thompson Sampling for Linear-Quadratic Control Problems
| Title | Thompson Sampling for Linear-Quadratic Control Problems |
| Authors | Marc Abeille, Alessandro Lazaric |
| Abstract | We consider the exploration-exploitation tradeoff in linear quadratic (LQ) control problems, where the state dynamics is linear and the cost function is quadratic in states and controls. We analyze the regret of Thompson sampling (TS) (a.k.a. posterior-sampling for reinforcement learning) in the frequentist setting, i.e., when the parameters characterizing the LQ dynamics are fixed. Despite the empirical and theoretical success in a wide range of problems from multi-armed bandit to linear bandit, we show that when studying the frequentist regret TS in control problems, we need to trade-off the frequency of sampling optimistic parameters and the frequency of switches in the control policy. This results in an overall regret of $O(T^{2/3})$, which is significantly worse than the regret $O(\sqrt{T})$ achieved by the optimism-in-face-of-uncertainty algorithm in LQ control problems. |
| Tasks | |
| Published | 2017-03-27 |
| URL | http://arxiv.org/abs/1703.08972v1 |
| http://arxiv.org/pdf/1703.08972v1.pdf | |
| PWC | https://paperswithcode.com/paper/thompson-sampling-for-linear-quadratic |
| Repo | |
| Framework | |
Deep learning for inferring cause of data anomalies
| Title | Deep learning for inferring cause of data anomalies |
| Authors | V. Azzolini, M. Borisyak, G. Cerminara, D. Derkach, G. Franzoni, F. De Guio, O. Koval, M. Pierini, A. Pol, F. Ratnikov, F. Siroky, A. Ustyuzhanin, J-R. Vlimant |
| Abstract | Daily operation of a large-scale experiment is a resource consuming task, particularly from perspectives of routine data quality monitoring. Typically, data comes from different sub-detectors and the global quality of data depends on the combinatorial performance of each of them. In this paper, the problem of identifying channels in which anomalies occurred is considered. We introduce a generic deep learning model and prove that, under reasonable assumptions, the model learns to identify ‘channels’ which are affected by an anomaly. Such model could be used for data quality manager cross-check and assistance and identifying good channels in anomalous data samples. The main novelty of the method is that the model does not require ground truth labels for each channel, only global flag is used. This effectively distinguishes the model from classical classification methods. Being applied to CMS data collected in the year 2010, this approach proves its ability to decompose anomaly by separate channels. |
| Tasks | |
| Published | 2017-11-19 |
| URL | http://arxiv.org/abs/1711.07051v1 |
| http://arxiv.org/pdf/1711.07051v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-learning-for-inferring-cause-of-data |
| Repo | |
| Framework | |
Spatial Filtering for EEG-Based Regression Problems in Brain-Computer Interface (BCI)
| Title | Spatial Filtering for EEG-Based Regression Problems in Brain-Computer Interface (BCI) |
| Authors | Dongrui Wu, Jung-Tai King, Chun-Hsiang Chuang, Chin-Teng Lin, Tzyy-Ping Jung |
| Abstract | Electroencephalogram (EEG) signals are frequently used in brain-computer interfaces (BCIs), but they are easily contaminated by artifacts and noises, so preprocessing must be done before they are fed into a machine learning algorithm for classification or regression. Spatial filters have been widely used to increase the signal-to-noise ratio of EEG for BCI classification problems, but their applications in BCI regression problems have been very limited. This paper proposes two common spatial pattern (CSP) filters for EEG-based regression problems in BCI, which are extended from the CSP filter for classification, by making use of fuzzy sets. Experimental results on EEG-based response speed estimation from a large-scale study, which collected 143 sessions of sustained-attention psychomotor vigilance task data from 17 subjects during a 5-month period, demonstrate that the two proposed spatial filters can significantly increase the EEG signal quality. When used in LASSO and k-nearest neighbors regression for user response speed estimation, the spatial filters can reduce the root mean square estimation error by 10.02-19.77%, and at the same time increase the correlation to the true response speed by 19.39-86.47%. |
| Tasks | EEG |
| Published | 2017-02-09 |
| URL | http://arxiv.org/abs/1702.02914v1 |
| http://arxiv.org/pdf/1702.02914v1.pdf | |
| PWC | https://paperswithcode.com/paper/spatial-filtering-for-eeg-based-regression |
| Repo | |
| Framework | |
Empirical analysis of non-linear activation functions for Deep Neural Networks in classification tasks
| Title | Empirical analysis of non-linear activation functions for Deep Neural Networks in classification tasks |
| Authors | Giovanni Alcantara |
| Abstract | We provide an overview of several non-linear activation functions in a neural network architecture that have proven successful in many machine learning applications. We conduct an empirical analysis on the effectiveness of using these function on the MNIST classification task, with the aim of clarifying which functions produce the best results overall. Based on this first set of results, we examine the effects of building deeper architectures with an increasing number of hidden layers. We also survey the impact of using, on the same task, different initialisation schemes for the weights of our neural network. Using these sets of experiments as a base, we conclude by providing a optimal neural network architecture that yields impressive results in accuracy on the MNIST classification task. |
| Tasks | |
| Published | 2017-10-30 |
| URL | http://arxiv.org/abs/1710.11272v1 |
| http://arxiv.org/pdf/1710.11272v1.pdf | |
| PWC | https://paperswithcode.com/paper/empirical-analysis-of-non-linear-activation |
| Repo | |
| Framework | |
Abnormal Spatial-Temporal Pattern Analysis for Niagara Frontier Border Wait Times
| Title | Abnormal Spatial-Temporal Pattern Analysis for Niagara Frontier Border Wait Times |
| Authors | Zhenhua Zhang, Lei Lin |
| Abstract | Border crossing delays cause problems like huge economics loss and heavy environmental pollutions. To understand more about the nature of border crossing delay, this study applies a dictionary-based compression algorithm to process the historical Niagara Frontier border wait times data. It can identify the abnormal spatial-temporal patterns for both passenger vehicles and trucks at three bridges connecting US and Canada. Furthermore, it provides a quantitate anomaly score to rank the wait times patterns across the three bridges for each vehicle type and each direction. By analyzing the top three most abnormal patterns, we find that there are at least two factors contributing the anomaly of the patterns. The weekends and holidays may cause unusual heave congestions at the three bridges at the same time, and the freight transportation demand may be uneven from Canada to the USA at Peace Bridge and Lewiston-Queenston Bridge, which may lead to a high anomaly score. By calculating the frequency of the top 5% abnormal patterns by hour of the day, the results show that for cars from the USA to Canada, the frequency of abnormal waiting time patterns is the highest during noon while for trucks in the same direction, it is the highest during the afternoon peak hours. For Canada to US direction, the frequency of abnormal border wait time patterns for both cars and trucks reaches to the peak during the afternoon. The analysis of abnormal spatial-temporal wait times patterns is promising to improve the border crossing management |
| Tasks | |
| Published | 2017-10-31 |
| URL | http://arxiv.org/abs/1711.00054v1 |
| http://arxiv.org/pdf/1711.00054v1.pdf | |
| PWC | https://paperswithcode.com/paper/abnormal-spatial-temporal-pattern-analysis |
| Repo | |
| Framework | |
Deep Hybrid Similarity Learning for Person Re-identification
| Title | Deep Hybrid Similarity Learning for Person Re-identification |
| Authors | Jianqing Zhu, Huanqiang Zeng, Shengcai Liao, Zhen Lei, Canhui Cai, LiXin Zheng |
| Abstract | Person Re-IDentification (Re-ID) aims to match person images captured from two non-overlapping cameras. In this paper, a deep hybrid similarity learning (DHSL) method for person Re-ID based on a convolution neural network (CNN) is proposed. In our approach, a CNN learning feature pair for the input image pair is simultaneously extracted. Then, both the element-wise absolute difference and multiplication of the CNN learning feature pair are calculated. Finally, a hybrid similarity function is designed to measure the similarity between the feature pair, which is realized by learning a group of weight coefficients to project the element-wise absolute difference and multiplication into a similarity score. Consequently, the proposed DHSL method is able to reasonably assign parameters of feature learning and metric learning in a CNN so that the performance of person Re-ID is improved. Experiments on three challenging person Re-ID databases, QMUL GRID, VIPeR and CUHK03, illustrate that the proposed DHSL method is superior to multiple state-of-the-art person Re-ID methods. |
| Tasks | Metric Learning, Person Re-Identification |
| Published | 2017-02-16 |
| URL | http://arxiv.org/abs/1702.04858v2 |
| http://arxiv.org/pdf/1702.04858v2.pdf | |
| PWC | https://paperswithcode.com/paper/deep-hybrid-similarity-learning-for-person-re |
| Repo | |
| Framework | |
From Query-By-Keyword to Query-By-Example: LinkedIn Talent Search Approach
| Title | From Query-By-Keyword to Query-By-Example: LinkedIn Talent Search Approach |
| Authors | Viet Ha-Thuc, Yan Yan, Xianren Wu, Vijay Dialani, Abhishek Gupta, Shakti Sinha |
| Abstract | One key challenge in talent search is to translate complex criteria of a hiring position into a search query, while it is relatively easy for a searcher to list examples of suitable candidates for a given position. To improve search efficiency, we propose the next generation of talent search at LinkedIn, also referred to as Search By Ideal Candidates. In this system, a searcher provides one or several ideal candidates as the input to hire for a given position. The system then generates a query based on the ideal candidates and uses it to retrieve and rank results. Shifting from the traditional Query-By-Keyword to this new Query-By-Example system poses a number of challenges: How to generate a query that best describes the candidates? When moving to a completely different paradigm, how does one leverage previous product logs to learn ranking models and/or evaluate the new system with no existing usage logs? Finally, given the different nature between the two search paradigms, the ranking features typically used for Query-By-Keyword systems might not be optimal for Query-By-Example. This paper describes our approach to solving these challenges. We present experimental results confirming the effectiveness of the proposed solution, particularly on query building and search ranking tasks. As of writing this paper, the new system has been available to all LinkedIn members. |
| Tasks | |
| Published | 2017-09-03 |
| URL | http://arxiv.org/abs/1709.00653v1 |
| http://arxiv.org/pdf/1709.00653v1.pdf | |
| PWC | https://paperswithcode.com/paper/from-query-by-keyword-to-query-by-example |
| Repo | |
| Framework | |
Integrating Additional Knowledge Into Estimation of Graphical Models
| Title | Integrating Additional Knowledge Into Estimation of Graphical Models |
| Authors | Yunqi Bu, Johannes Lederer |
| Abstract | In applications of graphical models, we typically have more information than just the samples themselves. A prime example is the estimation of brain connectivity networks based on fMRI data, where in addition to the samples themselves, the spatial positions of the measurements are readily available. With particular regard for this application, we are thus interested in ways to incorporate additional knowledge most effectively into graph estimation. Our approach to this is to make neighborhood selection receptive to additional knowledge by strengthening the role of the tuning parameters. We demonstrate that this concept (i) can improve reproducibility, (ii) is computationally convenient and efficient, and (iii) carries a lucid Bayesian interpretation. We specifically show that the approach provides effective estimations of brain connectivity graphs from fMRI data. However, providing a general scheme for the inclusion of additional knowledge, our concept is expected to have applications in a wide range of domains. |
| Tasks | |
| Published | 2017-04-10 |
| URL | http://arxiv.org/abs/1704.02739v2 |
| http://arxiv.org/pdf/1704.02739v2.pdf | |
| PWC | https://paperswithcode.com/paper/integrating-additional-knowledge-into |
| Repo | |
| Framework | |
Interpretable Deep Learning applied to Plant Stress Phenotyping
| Title | Interpretable Deep Learning applied to Plant Stress Phenotyping |
| Authors | Sambuddha Ghosal, David Blystone, Asheesh K. Singh, Baskar Ganapathysubramanian, Arti Singh, Soumik Sarkar |
| Abstract | Availability of an explainable deep learning model that can be applied to practical real world scenarios and in turn, can consistently, rapidly and accurately identify specific and minute traits in applicable fields of biological sciences, is scarce. Here we consider one such real world example viz., accurate identification, classification and quantification of biotic and abiotic stresses in crop research and production. Up until now, this has been predominantly done manually by visual inspection and require specialized training. However, such techniques are hindered by subjectivity resulting from inter- and intra-rater cognitive variability. Here, we demonstrate the ability of a machine learning framework to identify and classify a diverse set of foliar stresses in the soybean plant with remarkable accuracy. We also present an explanation mechanism using gradient-weighted class activation mapping that isolates the visual symptoms used by the model to make predictions. This unsupervised identification of unique visual symptoms for each stress provides a quantitative measure of stress severity, allowing for identification, classification and quantification in one framework. The learnt model appears to be agnostic to species and make good predictions for other (non-soybean) species, demonstrating an ability of transfer learning. |
| Tasks | Transfer Learning |
| Published | 2017-10-24 |
| URL | http://arxiv.org/abs/1710.08619v3 |
| http://arxiv.org/pdf/1710.08619v3.pdf | |
| PWC | https://paperswithcode.com/paper/interpretable-deep-learning-applied-to-plant |
| Repo | |
| Framework | |
Logical Inferences with Contexts of RDF Triples
| Title | Logical Inferences with Contexts of RDF Triples |
| Authors | Vinh Nguyen, Amit Sheth |
| Abstract | Logical inference, an integral feature of the Semantic Web, is the process of deriving new triples by applying entailment rules on knowledge bases. The entailment rules are determined by the model-theoretic semantics. Incorporating context of an RDF triple (e.g., provenance, time, and location) into the inferencing process requires the formal semantics to be capable of describing the context of RDF triples also in the form of triples, or in other words, RDF contextual triples about triples. The formal semantics should also provide the rules that could entail new contextual triples about triples. In this paper, we propose the first inferencing mechanism that allows context of RDF triples, represented in the form of RDF triples about triples, to be the first-class citizens in the model-theoretic semantics and in the logical rules. Our inference mechanism is well-formalized with all new concepts being captured in the model-theoretic semantics. This formal semantics also allows us to derive a new set of entailment rules that could entail new contextual triples about triples. To demonstrate the feasibility and the scalability of the proposed mechanism, we implement a new tool in which we transform the existing knowledge bases to our representation of RDF triples about triples and provide the option for this tool to compute the inferred triples for the proposed rules. We evaluate the computation of the proposed rules on a large scale using various real-world knowledge bases such as Bio2RDF NCBI Genes and DBpedia. The results show that the computation of the inferred triples can be highly scalable. On average, one billion inferred triples adds 5-6 minutes to the overall transformation process. NCBI Genes, with 20 billion triples in total, took only 232 minutes for the transformation of 12 billion triples and added 42 minutes for inferring 8 billion triples to the overall process. |
| Tasks | |
| Published | 2017-01-20 |
| URL | http://arxiv.org/abs/1701.05724v1 |
| http://arxiv.org/pdf/1701.05724v1.pdf | |
| PWC | https://paperswithcode.com/paper/logical-inferences-with-contexts-of-rdf |
| Repo | |
| Framework | |
