Paper Group ANR 603
Robust Iris Segmentation Based on Fully Convolutional Networks and Generative Adversarial Networks. An elementary derivation of the Chinese restaurant process from Sethuraman’s stick-breaking process. Classification of breast cancer histology images using transfer learning. Facebook Reaction-Based Emotion Classifier as Cue for Sarcasm Detection. Gu …
Robust Iris Segmentation Based on Fully Convolutional Networks and Generative Adversarial Networks
Title | Robust Iris Segmentation Based on Fully Convolutional Networks and Generative Adversarial Networks |
Authors | Cides S. Bezerra, Rayson Laroca, Diego R. Lucio, Evair Severo, Lucas F. Oliveira, Alceu S. Britto Jr., David Menotti |
Abstract | The iris can be considered as one of the most important biometric traits due to its high degree of uniqueness. Iris-based biometrics applications depend mainly on the iris segmentation whose suitability is not robust for different environments such as near-infrared (NIR) and visible (VIS) ones. In this paper, two approaches for robust iris segmentation based on Fully Convolutional Networks (FCNs) and Generative Adversarial Networks (GANs) are described. Similar to a common convolutional network, but without the fully connected layers (i.e., the classification layers), an FCN employs at its end a combination of pooling layers from different convolutional layers. Based on the game theory, a GAN is designed as two networks competing with each other to generate the best segmentation. The proposed segmentation networks achieved promising results in all evaluated datasets (i.e., BioSec, CasiaI3, CasiaT4, IITD-1) of NIR images and (NICE.I, CrEye-Iris and MICHE-I) of VIS images in both non-cooperative and cooperative domains, outperforming the baselines techniques which are the best ones found so far in the literature, i.e., a new state of the art for these datasets. Furthermore, we manually labeled 2,431 images from CasiaT4, CrEye-Iris and MICHE-I datasets, making the masks available for research purposes. |
Tasks | Iris Segmentation |
Published | 2018-09-04 |
URL | http://arxiv.org/abs/1809.00769v1 |
http://arxiv.org/pdf/1809.00769v1.pdf | |
PWC | https://paperswithcode.com/paper/robust-iris-segmentation-based-on-fully |
Repo | |
Framework | |
An elementary derivation of the Chinese restaurant process from Sethuraman’s stick-breaking process
Title | An elementary derivation of the Chinese restaurant process from Sethuraman’s stick-breaking process |
Authors | Jeffrey W. Miller |
Abstract | The Chinese restaurant process (CRP) and the stick-breaking process are the two most commonly used representations of the Dirichlet process. However, the usual proof of the connection between them is indirect, relying on abstract properties of the Dirichlet process that are difficult for nonexperts to verify. This short note provides a direct proof that the stick-breaking process leads to the CRP, without using any measure theory. We also discuss how the stick-breaking representation arises naturally from the CRP. |
Tasks | |
Published | 2018-01-01 |
URL | http://arxiv.org/abs/1801.00513v3 |
http://arxiv.org/pdf/1801.00513v3.pdf | |
PWC | https://paperswithcode.com/paper/an-elementary-derivation-of-the-chinese |
Repo | |
Framework | |
Classification of breast cancer histology images using transfer learning
Title | Classification of breast cancer histology images using transfer learning |
Authors | Sulaiman Vesal, Nishant Ravikumar, AmirAbbas Davari, Stephan Ellmann, Andreas Maier |
Abstract | Breast cancer is one of the leading causes of mortality in women. Early detection and treatment are imperative for improving survival rates, which have steadily increased in recent years as a result of more sophisticated computer-aided-diagnosis (CAD) systems. A critical component of breast cancer diagnosis relies on histopathology, a laborious and highly subjective process. Consequently, CAD systems are essential to reduce inter-rater variability and supplement the analyses conducted by specialists. In this paper, a transfer-learning based approach is proposed, for the task of breast histology image classification into four tissue sub-types, namely, normal, benign, \textit{in situ} carcinoma and invasive carcinoma. The histology images, provided as part of the BACH 2018 grand challenge, were first normalized to correct for color variations resulting from inconsistencies during slide preparation. Subsequently, image patches were extracted and used to fine-tune Google`s Inception-V3 and ResNet50 convolutional neural networks (CNNs), both pre-trained on the ImageNet database, enabling them to learn domain-specific features, necessary to classify the histology images. The ResNet50 network (based on residual learning) achieved a test classification accuracy of 97.50% for four classes, outperforming the Inception-V3 network which achieved an accuracy of 91.25%. | |
Tasks | Classification Of Breast Cancer Histology Images, Image Classification, Transfer Learning |
Published | 2018-02-26 |
URL | http://arxiv.org/abs/1802.09424v1 |
http://arxiv.org/pdf/1802.09424v1.pdf | |
PWC | https://paperswithcode.com/paper/classification-of-breast-cancer-histology-1 |
Repo | |
Framework | |
Facebook Reaction-Based Emotion Classifier as Cue for Sarcasm Detection
Title | Facebook Reaction-Based Emotion Classifier as Cue for Sarcasm Detection |
Authors | Po Chen Kuo, Fernando H. Calderon Alvarado, Yi-Shin Chen |
Abstract | Online social media users react to content in them based on context. Emotions or mood play a significant part of these reactions, which has filled these platforms with opinionated content. Different approaches and applications to make better use of this data are continuously being developed. However, due to the nature of the data, the variety of platforms, and dynamic online user behavior, there are still many issues to be dealt with. It remains a challenge to properly obtain a reliable emotional status from a user prior to posting a comment. This work introduces a methodology that explores semi-supervised multilingual emotion detection based on the overlap of Facebook reactions and textual data. With the resulting emotion detection system we evaluate the possibility of using emotions and user behavior features for the task of sarcasm detection. More than 1 million English and Chinese comments from over 62,000 public Facebook pages posts have been collected and processed, conducted experiments show acceptable performance metrics. |
Tasks | Sarcasm Detection |
Published | 2018-05-04 |
URL | http://arxiv.org/abs/1805.06510v1 |
http://arxiv.org/pdf/1805.06510v1.pdf | |
PWC | https://paperswithcode.com/paper/facebook-reaction-based-emotion-classifier-as |
Repo | |
Framework | |
Guaranteed satisficing and finite regret: Analysis of a cognitive satisficing value function
Title | Guaranteed satisficing and finite regret: Analysis of a cognitive satisficing value function |
Authors | Akihiro Tamatsukuri, Tatsuji Takahashi |
Abstract | As reinforcement learning algorithms are being applied to increasingly complicated and realistic tasks, it is becoming increasingly difficult to solve such problems within a practical time frame. Hence, we focus on a \textit{satisficing} strategy that looks for an action whose value is above the aspiration level (analogous to the break-even point), rather than the optimal action. In this paper, we introduce a simple mathematical model called risk-sensitive satisficing ($RS$) that implements a satisficing strategy by integrating risk-averse and risk-prone attitudes under the greedy policy. We apply the proposed model to the $K$-armed bandit problems, which constitute the most basic class of reinforcement learning tasks, and prove two propositions. The first is that $RS$ is guaranteed to find an action whose value is above the aspiration level. The second is that the regret (expected loss) of $RS$ is upper bounded by a finite value, given that the aspiration level is set to an “optimal level” so that satisficing implies optimizing. We confirm the results through numerical simulations and compare the performance of $RS$ with that of other representative algorithms for the $K$-armed bandit problems. |
Tasks | |
Published | 2018-12-14 |
URL | http://arxiv.org/abs/1812.05795v2 |
http://arxiv.org/pdf/1812.05795v2.pdf | |
PWC | https://paperswithcode.com/paper/guaranteed-satisficing-and-finite-regret |
Repo | |
Framework | |
Linguistic unit discovery from multi-modal inputs in unwritten languages: Summary of the “Speaking Rosetta” JSALT 2017 Workshop
Title | Linguistic unit discovery from multi-modal inputs in unwritten languages: Summary of the “Speaking Rosetta” JSALT 2017 Workshop |
Authors | Odette Scharenborg, Laurent Besacier, Alan Black, Mark Hasegawa-Johnson, Florian Metze, Graham Neubig, Sebastian Stueker, Pierre Godard, Markus Mueller, Lucas Ondel, Shruti Palaskar, Philip Arthur, Francesco Ciannella, Mingxing Du, Elin Larsen, Danny Merkx, Rachid Riad, Liming Wang, Emmanuel Dupoux |
Abstract | We summarize the accomplishments of a multi-disciplinary workshop exploring the computational and scientific issues surrounding the discovery of linguistic units (subwords and words) in a language without orthography. We study the replacement of orthographic transcriptions by images and/or translated text in a well-resourced language to help unsupervised discovery from raw speech. |
Tasks | |
Published | 2018-02-14 |
URL | http://arxiv.org/abs/1802.05092v1 |
http://arxiv.org/pdf/1802.05092v1.pdf | |
PWC | https://paperswithcode.com/paper/linguistic-unit-discovery-from-multi-modal |
Repo | |
Framework | |
A Fast, Principled Working Set Algorithm for Exploiting Piecewise Linear Structure in Convex Problems
Title | A Fast, Principled Working Set Algorithm for Exploiting Piecewise Linear Structure in Convex Problems |
Authors | Tyler B. Johnson, Carlos Guestrin |
Abstract | By reducing optimization to a sequence of smaller subproblems, working set algorithms achieve fast convergence times for many machine learning problems. Despite such performance, working set implementations often resort to heuristics to determine subproblem size, makeup, and stopping criteria. We propose BlitzWS, a working set algorithm with useful theoretical guarantees. Our theory relates subproblem size and stopping criteria to the amount of progress during each iteration. This result motivates strategies for optimizing algorithmic parameters and discarding irrelevant components as BlitzWS progresses toward a solution. BlitzWS applies to many convex problems, including training L1-regularized models and support vector machines. We showcase this versatility with empirical comparisons, which demonstrate BlitzWS is indeed a fast algorithm. |
Tasks | |
Published | 2018-07-20 |
URL | http://arxiv.org/abs/1807.08046v1 |
http://arxiv.org/pdf/1807.08046v1.pdf | |
PWC | https://paperswithcode.com/paper/a-fast-principled-working-set-algorithm-for |
Repo | |
Framework | |
Attended Temperature Scaling: A Practical Approach for Calibrating Deep Neural Networks
Title | Attended Temperature Scaling: A Practical Approach for Calibrating Deep Neural Networks |
Authors | Azadeh Sadat Mozafari, Hugo Siqueira Gomes, Wilson Leão, Steeven Janny, Christian Gagné |
Abstract | Recently, Deep Neural Networks (DNNs) have been achieving impressive results on wide range of tasks. However, they suffer from being well-calibrated. In decision-making applications, such as autonomous driving or medical diagnosing, the confidence of deep networks plays an important role to bring the trust and reliability to the system. To calibrate the deep networks’ confidence, many probabilistic and measure-based approaches are proposed. Temperature Scaling (TS) is a state-of-the-art among measure-based calibration methods which has low time and memory complexity as well as effectiveness. In this paper, we study TS and show it does not work properly when the validation set that TS uses for calibration has small size or contains noisy-labeled samples. TS also cannot calibrate highly accurate networks as well as non-highly accurate ones. Accordingly, we propose Attended Temperature Scaling (ATS) which preserves the advantages of TS while improves calibration in aforementioned challenging situations. We provide theoretical justifications for ATS and assess its effectiveness on wide range of deep models and datasets. We also compare the calibration results of TS and ATS on skin lesion detection application as a practical problem where well-calibrated system can play important role in making a decision. |
Tasks | Autonomous Driving, Calibration, Decision Making |
Published | 2018-10-27 |
URL | https://arxiv.org/abs/1810.11586v3 |
https://arxiv.org/pdf/1810.11586v3.pdf | |
PWC | https://paperswithcode.com/paper/a-new-loss-function-for-temperature-scaling |
Repo | |
Framework | |
Towards Automatic Discovery of Cybercrime Supply Chains
Title | Towards Automatic Discovery of Cybercrime Supply Chains |
Authors | Rasika Bhalerao, Maxwell Aliapoulios, Ilia Shumailov, Sadia Afroz, Damon McCoy |
Abstract | Cybercrime forums enable modern criminal entrepreneurs to collaborate with other criminals into increasingly efficient and sophisticated criminal endeavors. Understanding the connections between different products and services can often illuminate effective interventions. However, generating this understanding of supply chains currently requires time-consuming manual effort. In this paper, we propose a language-agnostic method to automatically extract supply chains from cybercrime forum posts and replies. Our supply chain detection algorithm can identify 36% and 58% relevant chains within major English and Russian forums, respectively, showing improvements over the baselines of 13% and 36%, respectively. Our analysis of the automatically generated supply chains demonstrates underlying connections between products and services within these forums. For example, the extracted supply chain illuminated the connection between hack-for-hire services and the selling of rare and valuable `OG’ accounts, which has only recently been reported. The understanding of connections between products and services exposes potentially effective intervention points. | |
Tasks | |
Published | 2018-12-02 |
URL | http://arxiv.org/abs/1812.00381v2 |
http://arxiv.org/pdf/1812.00381v2.pdf | |
PWC | https://paperswithcode.com/paper/towards-automatic-discovery-of-cybercrime |
Repo | |
Framework | |
Segmentation of Skin Lesions and their Attributes Using Multi-Scale Convolutional Neural Networks and Domain Specific Augmentations
Title | Segmentation of Skin Lesions and their Attributes Using Multi-Scale Convolutional Neural Networks and Domain Specific Augmentations |
Authors | Mostafa Jahanifar, Neda Zamani Tajeddin, Navid Alemi Koohbanani, Ali Gooya, Nasir Rajpoot |
Abstract | Computer-aided diagnosis systems for classification of different type of skin lesions have been an active field of research in recent decades. It has been shown that introducing lesions and their attributes masks into lesion classification pipeline can greatly improve the performance. In this paper, we propose a framework by incorporating transfer learning for segmenting lesions and their attributes based on the convolutional neural networks. The proposed framework is based on the encoder-decoder architecture which utilizes a variety of pre-trained networks in the encoding path and generates the prediction map by combining multi-scale information in decoding path using a pyramid pooling manner. To address the lack of training data and increase the proposed model generalization, an extensive set of novel domain-specific augmentation routines have been applied to simulate the real variations in dermoscopy images. Finally, by performing broad experiments on three different data sets obtained from International Skin Imaging Collaboration archive (ISIC2016, ISIC2017, and ISIC2018 challenges data sets), we show that the proposed method outperforms other state-of-the-art approaches for ISIC2016 and ISIC2017 segmentation task and achieved the first rank on the leader-board of ISIC2018 attribute detection task. |
Tasks | Transfer Learning |
Published | 2018-09-23 |
URL | http://arxiv.org/abs/1809.10243v3 |
http://arxiv.org/pdf/1809.10243v3.pdf | |
PWC | https://paperswithcode.com/paper/leveraging-transfer-learning-for-segmenting |
Repo | |
Framework | |
Deep Graphs
Title | Deep Graphs |
Authors | Emmanouil Antonios Platanios, Alex Smola |
Abstract | We propose an algorithm for deep learning on networks and graphs. It relies on the notion that many graph algorithms, such as PageRank, Weisfeiler-Lehman, or Message Passing can be expressed as iterative vertex updates. Unlike previous methods which rely on the ingenuity of the designer, Deep Graphs are adaptive to the estimation problem. Training and deployment are both efficient, since the cost is $O(E + V)$, where $E$ and $V$ are the sets of edges and vertices respectively. In short, we learn the recurrent update functions rather than positing their specific functional form. This yields an algorithm that achieves excellent accuracy on both graph labeling and regression tasks. |
Tasks | |
Published | 2018-06-04 |
URL | http://arxiv.org/abs/1806.01235v1 |
http://arxiv.org/pdf/1806.01235v1.pdf | |
PWC | https://paperswithcode.com/paper/deep-graphs |
Repo | |
Framework | |
Simple Root Cause Analysis by Separable Likelihoods
Title | Simple Root Cause Analysis by Separable Likelihoods |
Authors | Maciej Skorski |
Abstract | Root Cause Analysis for Anomalies is challenging because of the trade-off between the accuracy and its explanatory friendliness, required for industrial applications. In this paper we propose a framework for simple and friendly RCA within the Bayesian regime under certain restrictions (that Hessian at the mode is diagonal, here referred to as \emph{separability}) imposed on the predictive posterior. We show that this assumption is satisfied for important base models, including Multinomal, Dirichlet-Multinomial and Naive Bayes. To demonstrate the usefulness of the framework, we embed it into the Bayesian Net and validate on web server error logs (real world data set). |
Tasks | |
Published | 2018-08-13 |
URL | http://arxiv.org/abs/1808.04302v1 |
http://arxiv.org/pdf/1808.04302v1.pdf | |
PWC | https://paperswithcode.com/paper/simple-root-cause-analysis-by-separable |
Repo | |
Framework | |
Query K-means Clustering and the Double Dixie Cup Problem
Title | Query K-means Clustering and the Double Dixie Cup Problem |
Authors | I Chien, Chao Pan, Olgica Milenkovic |
Abstract | We consider the problem of approximate $K$-means clustering with outliers and side information provided by same-cluster queries and possibly noisy answers. Our solution shows that, under some mild assumptions on the smallest cluster size, one can obtain an $(1+\epsilon)$-approximation for the optimal potential with probability at least $1-\delta$, where $\epsilon>0$ and $\delta\in(0,1)$, using an expected number of $O(\frac{K^3}{\epsilon \delta})$ noiseless same-cluster queries and comparison-based clustering of complexity $O(ndK + \frac{K^3}{\epsilon \delta})$, here, $n$ denotes the number of points and $d$ the dimension of space. Compared to a handful of other known approaches that perform importance sampling to account for small cluster sizes, the proposed query technique reduces the number of queries by a factor of roughly $O(\frac{K^6}{\epsilon^3})$, at the cost of possibly missing very small clusters. We extend this settings to the case where some queries to the oracle produce erroneous information, and where certain points, termed outliers, do not belong to any clusters. Our proof techniques differ from previous methods used for $K$-means clustering analysis, as they rely on estimating the sizes of the clusters and the number of points needed for accurate centroid estimation and subsequent nontrivial generalizations of the double Dixie cup problem. We illustrate the performance of the proposed algorithm both on synthetic and real datasets, including MNIST and CIFAR $10$. |
Tasks | |
Published | 2018-06-15 |
URL | http://arxiv.org/abs/1806.05938v2 |
http://arxiv.org/pdf/1806.05938v2.pdf | |
PWC | https://paperswithcode.com/paper/query-k-means-clustering-and-the-double-dixie |
Repo | |
Framework | |
Window Opening Model using Deep Learning Methods
Title | Window Opening Model using Deep Learning Methods |
Authors | Romana Markovic, Eva Grintal, Daniel Wölki, Jérôme Frisch, Christoph van Treeck |
Abstract | Occupant behavior (OB) and in particular window openings need to be considered in building performance simulation (BPS), in order to realistically model the indoor climate and energy consumption for heating ventilation and air conditioning (HVAC). However, the proposed OB window opening models are often biased towards the over-represented class where windows remained closed. In addition, they require tuning for each occupant which can not be efficiently scaled to the increased number of occupants. This paper presents a window opening model for commercial buildings using deep learning methods. The model is trained using data from occupants from an office building in Germany. In total the model is evaluated using almost 20 mio. data points from 3 independent buildings, located in Aachen, Frankfurt and Philadelphia. Eventually, the results of 3100 core hours of model development are summarized, which makes this study the largest of its kind in window states modeling. Additionally, the practical potential of the proposed model was tested by incorporating it in the Modelica-based thermal building simulation. The resulting evaluation accuracy and F1 scores on the office buildings ranged between 86-89 % and 0.53-0.65 respectively. The performance dropped around 15 % points in case of sparse input data, while the F1 score remained high. |
Tasks | |
Published | 2018-07-10 |
URL | http://arxiv.org/abs/1807.03610v3 |
http://arxiv.org/pdf/1807.03610v3.pdf | |
PWC | https://paperswithcode.com/paper/window-opening-model-using-deep-learning |
Repo | |
Framework | |
A Margin-based MLE for Crowdsourced Partial Ranking
Title | A Margin-based MLE for Crowdsourced Partial Ranking |
Authors | Qianqian Xu, Jiechao Xiong, Xinwei Sun, Zhiyong Yang, Xiaochun Cao, Qingming Huang, Yuan Yao |
Abstract | A preference order or ranking aggregated from pairwise comparison data is commonly understood as a strict total order. However, in real-world scenarios, some items are intrinsically ambiguous in comparisons, which may very well be an inherent uncertainty of the data. In this case, the conventional total order ranking can not capture such uncertainty with mere global ranking or utility scores. In this paper, we are specifically interested in the recent surge in crowdsourcing applications to predict partial but more accurate (i.e., making less incorrect statements) orders rather than complete ones. To do so, we propose a novel framework to learn some probabilistic models of partial orders as a \emph{margin-based Maximum Likelihood Estimate} (MLE) method. We prove that the induced MLE is a joint convex optimization problem with respect to all the parameters, including the global ranking scores and margin parameter. Moreover, three kinds of generalized linear models are studied, including the basic uniform model, Bradley-Terry model, and Thurstone-Mosteller model, equipped with some theoretical analysis on FDR and Power control for the proposed methods. The validity of these models are supported by experiments with both simulated and real-world datasets, which shows that the proposed models exhibit improvements compared with traditional state-of-the-art algorithms. |
Tasks | |
Published | 2018-07-29 |
URL | http://arxiv.org/abs/1807.11014v1 |
http://arxiv.org/pdf/1807.11014v1.pdf | |
PWC | https://paperswithcode.com/paper/a-margin-based-mle-for-crowdsourced-partial |
Repo | |
Framework | |