Paper Group ANR 1769
Visual Diagnosis of Dermatological Disorders: Human and Machine Performance. Extending the Service Composition Formalism with Relational Parameters. A Fast Saddle-Point Dynamical System Approach to Robust Deep Learning. LSTM-MSNet: Leveraging Forecasts on Sets of Related Time Series with Multiple Seasonal Patterns. DREAMT – Embodied Motivational C …
Visual Diagnosis of Dermatological Disorders: Human and Machine Performance
| Title | Visual Diagnosis of Dermatological Disorders: Human and Machine Performance |
| Authors | Jeremy Kawahara, Ghassan Hamarneh |
| Abstract | Skin conditions are a global health concern, ranking the fourth highest cause of nonfatal disease burden when measured as years lost due to disability. As diagnosing, or classifying, skin diseases can help determine effective treatment, dermatologists have extensively researched how to diagnose conditions from a patient’s history and the lesion’s visual appearance. Computer vision researchers are attempting to encode this diagnostic ability into machines, and several recent studies report machine level performance comparable with dermatologists. This report reviews machine approaches to classify skin images and consider their performance when compared to human dermatologists. Following an overview of common image modalities, dermatologists’ diagnostic approaches and common tasks, and publicly available datasets, we discuss approaches to machine skin lesion classification. We then review works that directly compare human and machine performance. Finally, this report addresses the limitations and sources of errors in image-based skin disease diagnosis, applicable to both machines and dermatologists in a teledermatology setting. |
| Tasks | Skin Lesion Classification |
| Published | 2019-06-04 |
| URL | https://arxiv.org/abs/1906.01256v1 |
| https://arxiv.org/pdf/1906.01256v1.pdf | |
| PWC | https://paperswithcode.com/paper/visual-diagnosis-of-dermatological-disorders |
| Repo | |
| Framework | |
Extending the Service Composition Formalism with Relational Parameters
| Title | Extending the Service Composition Formalism with Relational Parameters |
| Authors | Paul Diac, Liana Tucar, Radu Mereuta |
| Abstract | Web Service Composition deals with the (re)use of Web Services to provide complex functionality, inexistent in any single service. Over the state-of-the-art, we introduce a new type of modeling, based on ontologies and relations between objects, which allows us to extend the expressiveness of problems that can be solved automatically. |
| Tasks | |
| Published | 2019-09-10 |
| URL | https://arxiv.org/abs/1909.04393v1 |
| https://arxiv.org/pdf/1909.04393v1.pdf | |
| PWC | https://paperswithcode.com/paper/extending-the-service-composition-formalism |
| Repo | |
| Framework | |
A Fast Saddle-Point Dynamical System Approach to Robust Deep Learning
| Title | A Fast Saddle-Point Dynamical System Approach to Robust Deep Learning |
| Authors | Yasaman Esfandiari, Aditya Balu, Keivan Ebrahimi, Umesh Vaidya, Nicola Elia, Soumik Sarkar |
| Abstract | Recent focus on robustness to adversarial attacks for deep neural networks produced a large variety of algorithms for training robust models. Most of the effective algorithms involve solving the min-max optimization problem for training robust models (min step) under worst-case attacks (max step). However, they often suffer from high computational cost from running several inner maximization iterations (to find an optimal attack) inside every outer minimization iteration. Therefore, it becomes difficult to readily apply such algorithms for moderate to large size real world data sets. To alleviate this, we explore the effectiveness of iterative descent-ascent algorithms where the maximization and minimization steps are executed in an alternate fashion to simultaneously obtain the worst-case attack and the corresponding robust model. Specifically, we propose a novel discrete-time dynamical system-based algorithm that aims to find the saddle point of a min-max optimization problem in the presence of uncertainties. Under the assumptions that the cost function is convex and uncertainties enter concavely in the robust learning problem, we analytically show that our algorithm converges asymptotically to the robust optimal solution under a general adversarial budget constraints as induced by $\ell_p$ norm, for $1\leq p\leq \infty$. Based on our proposed analysis, we devise a fast robust training algorithm for deep neural networks. Although such training involves highly non-convex robust optimization problems, empirical results show that the algorithm can achieve significant robustness compared to other state-of-the-art robust models on benchmark data sets. |
| Tasks | |
| Published | 2019-10-18 |
| URL | https://arxiv.org/abs/1910.08623v2 |
| https://arxiv.org/pdf/1910.08623v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-saddle-point-dynamical-system-approach-for |
| Repo | |
| Framework | |
LSTM-MSNet: Leveraging Forecasts on Sets of Related Time Series with Multiple Seasonal Patterns
| Title | LSTM-MSNet: Leveraging Forecasts on Sets of Related Time Series with Multiple Seasonal Patterns |
| Authors | Kasun Bandara, Christoph Bergmeir, Hansika Hewamalage |
| Abstract | Generating forecasts for time series with multiple seasonal cycles is an important use-case for many industries nowadays. Accounting for the multi-seasonal patterns becomes necessary to generate more accurate and meaningful forecasts in these contexts. In this paper, we propose Long Short-Term Memory Multi-Seasonal Net (LSTM-MSNet), a decompositionbased, unified prediction framework to forecast time series with multiple seasonal patterns. The current state of the art in this space are typically univariate methods, in which the model parameters of each time series are estimated independently. Consequently, these models are unable to include key patterns and structures that may be shared by a collection of time series. In contrast, LSTM-MSNet is a globally trained Long Short-Term Memory network (LSTM), where a single prediction model is built across all the available time series to exploit the crossseries knowledge in a group of related time series. Furthermore, our methodology combines a series of state-of-the-art multiseasonal decomposition techniques to supplement the LSTM learning procedure. In our experiments, we are able to show that on datasets from disparate data sources, like e.g. the popular M4 forecasting competition, a decomposition step is beneficial, whereas in the common real-world situation of homogeneous series from a single application, exogenous seasonal variables or no seasonal preprocessing at all are better choices. All options are readily included in the framework and allow us to achieve competitive results for both cases, outperforming many state-ofthe-art multi-seasonal forecasting methods |
| Tasks | Time Series |
| Published | 2019-09-10 |
| URL | https://arxiv.org/abs/1909.04293v1 |
| https://arxiv.org/pdf/1909.04293v1.pdf | |
| PWC | https://paperswithcode.com/paper/lstm-msnet-leveraging-forecasts-on-sets-of |
| Repo | |
| Framework | |
DREAMT – Embodied Motivational Conversational Storytelling
| Title | DREAMT – Embodied Motivational Conversational Storytelling |
| Authors | David M W Powers |
| Abstract | Storytelling is fundamental to language, including culture, conversation and communication in their broadest senses. It thus emerges as an essential component of intelligent systems, including systems where natural language is not a primary focus or where we do not usually think of a story being involved. In this paper we explore the emergence of storytelling as a requirement in embodied conversational agents, including its role in educational and health interventions, as well as in a general-purpose computer interface for people with disabilities or other constraints that prevent the use of traditional keyboard and speech interfaces. We further present a characterization of storytelling as an inventive fleshing out of detail according to a particular personal perspective, and propose the DREAMT model to focus attention on the different layers that need to be present in a character-driven storytelling system. Most if not all aspects of the DREAMT model have arisen from or been explored in some aspect of our implemented research systems, but currently only at a primitive and relatively unintegrated level. However, this experience leads us to formalize and elaborate the DREAMT model mnemonically as follows: - Description/Dialogue/Definition/Denotation - Realization/Representation/Role - Explanation/Education/Entertainment - Actualization/Activation - Motivation/Modelling - Topicalization/Transformation |
| Tasks | |
| Published | 2019-07-19 |
| URL | https://arxiv.org/abs/1907.09293v1 |
| https://arxiv.org/pdf/1907.09293v1.pdf | |
| PWC | https://paperswithcode.com/paper/dreamt-embodied-motivational-conversational |
| Repo | |
| Framework | |
A real-time iterative machine learning approach for temperature profile prediction in additive manufacturing processes
| Title | A real-time iterative machine learning approach for temperature profile prediction in additive manufacturing processes |
| Authors | Arindam Paul, Mojtaba Mozaffar, Zijiang Yang, Wei-keng Liao, Alok Choudhary, Jian Cao, Ankit Agrawal |
| Abstract | Additive Manufacturing (AM) is a manufacturing paradigm that builds three-dimensional objects from a computer-aided design model by successively adding material layer by layer. AM has become very popular in the past decade due to its utility for fast prototyping such as 3D printing as well as manufacturing functional parts with complex geometries using processes such as laser metal deposition that would be difficult to create using traditional machining. As the process for creating an intricate part for an expensive metal such as Titanium is prohibitive with respect to cost, computational models are used to simulate the behavior of AM processes before the experimental run. However, as the simulations are computationally costly and time-consuming for predicting multiscale multi-physics phenomena in AM, physics-informed data-driven machine-learning systems for predicting the behavior of AM processes are immensely beneficial. Such models accelerate not only multiscale simulation tools but also empower real-time control systems using in-situ data. In this paper, we design and develop essential components of a scientific framework for developing a data-driven model-based real-time control system. Finite element methods are employed for solving time-dependent heat equations and developing the database. The proposed framework uses extremely randomized trees - an ensemble of bagged decision trees as the regression algorithm iteratively using temperatures of prior voxels and laser information as inputs to predict temperatures of subsequent voxels. The models achieve mean absolute percentage errors below 1% for predicting temperature profiles for AM processes. The code is made available for the research community at https://github.com/paularindam/ml-iter-additive. |
| Tasks | |
| Published | 2019-07-28 |
| URL | https://arxiv.org/abs/1907.12953v2 |
| https://arxiv.org/pdf/1907.12953v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-real-time-iterative-machine-learning |
| Repo | |
| Framework | |
TopoResNet: A hybrid deep learning architecture and its application to skin lesion classification
| Title | TopoResNet: A hybrid deep learning architecture and its application to skin lesion classification |
| Authors | Yu-Min Chung, Chuan-Shen Hu, Austin Lawson, Clifford Smyth |
| Abstract | Skin cancer is one of the most common cancers in the United States. As technological advancements are made, algorithmic diagnosis of skin lesions is becoming more important. In this paper, we develop algorithms for segmenting the actual diseased area of skin in a given image of a skin lesion, and for classifying different types of skin lesions pictured in a given image. The cores of the algorithms used were based in persistent homology, an algebraic topology technique that is part of the rising field of Topological Data Analysis (TDA). The segmentation algorithm utilizes a similar concept to persistent homology that captures the robustness of segmented regions. For classification, we design two families of topological features from persistence diagrams—which we refer to as {\em persistence statistics} (PS) and {\em persistence curves} (PC), and use linear support vector machine as classifiers. We also combined those topological features, PS and PC, into ResNet-101 model, which we call {\em TopoResNet-101}, the results show that PS and PC are effective in two folds—improving classification performances and stabilizing the training process. Although convolutional features are the most important learning targets in CNN models, global information of images may be lost in the training process. Because topological features were extracted globally, our results show that the global property of topological features provide additional information to machine learning models. |
| Tasks | Skin Lesion Classification, Topological Data Analysis |
| Published | 2019-05-13 |
| URL | https://arxiv.org/abs/1905.08607v1 |
| https://arxiv.org/pdf/1905.08607v1.pdf | |
| PWC | https://paperswithcode.com/paper/190508607 |
| Repo | |
| Framework | |
SAGA with Arbitrary Sampling
| Title | SAGA with Arbitrary Sampling |
| Authors | Xu Qian, Zheng Qu, Peter Richtárik |
| Abstract | We study the problem of minimizing the average of a very large number of smooth functions, which is of key importance in training supervised learning models. One of the most celebrated methods in this context is the SAGA algorithm. Despite years of research on the topic, a general-purpose version of SAGA—one that would include arbitrary importance sampling and minibatching schemes—does not exist. We remedy this situation and propose a general and flexible variant of SAGA following the {\em arbitrary sampling} paradigm. We perform an iteration complexity analysis of the method, largely possible due to the construction of new stochastic Lyapunov functions. We establish linear convergence rates in the smooth and strongly convex regime, and under a quadratic functional growth condition (i.e., in a regime not assuming strong convexity). Our rates match those of the primal-dual method Quartz for which an arbitrary sampling analysis is available, which makes a significant step towards closing the gap in our understanding of complexity of primal and dual methods for finite sum problems. |
| Tasks | |
| Published | 2019-01-24 |
| URL | http://arxiv.org/abs/1901.08669v1 |
| http://arxiv.org/pdf/1901.08669v1.pdf | |
| PWC | https://paperswithcode.com/paper/saga-with-arbitrary-sampling |
| Repo | |
| Framework | |
On the Expressiveness of Approximate Inference in Bayesian Neural Networks
| Title | On the Expressiveness of Approximate Inference in Bayesian Neural Networks |
| Authors | Andrew Y. K. Foong, David R. Burt, Yingzhen Li, Richard E. Turner |
| Abstract | While Bayesian neural networks (BNNs) hold the promise of being flexible, well-calibrated statistical models, inference often requires poorly understood approximations. We study the impact of approximate inference in BNNs on the quality of uncertainty quantification, focusing on methods that use parametric approximating distributions. For single-hidden layer ReLU BNNs, we prove a fundamental limitation in function-space of two of the most ubiquitous distributions defined in weight-space: mean-field Gaussian and Monte Carlo dropout. In particular, neither method can have substantially increased uncertainty in between well-separated regions of low uncertainty. In contrast, for deep networks, we prove a universality result showing that there exist distributions in the above classes which provide flexible uncertainty estimates. However, we find that in practice pathologies of the same form as in the single-hidden layer case often persist when performing variational inference in deeper networks. Our results motivate careful consideration of the implications of approximate inference methods in BNNs. |
| Tasks | Active Learning, Bayesian Inference, Bayesian Optimisation, Decision Making |
| Published | 2019-09-02 |
| URL | https://arxiv.org/abs/1909.00719v3 |
| https://arxiv.org/pdf/1909.00719v3.pdf | |
| PWC | https://paperswithcode.com/paper/pathologies-of-factorised-gaussian-and-mc |
| Repo | |
| Framework | |
Automated Skin Lesion Classification Using Ensemble of Deep Neural Networks in ISIC 2018: Skin Lesion Analysis Towards Melanoma Detection Challenge
| Title | Automated Skin Lesion Classification Using Ensemble of Deep Neural Networks in ISIC 2018: Skin Lesion Analysis Towards Melanoma Detection Challenge |
| Authors | Md Ashraful Alam Milton |
| Abstract | In this paper, we studied extensively on different deep learning based methods to detect melanoma and skin lesion cancers. Melanoma, a form of malignant skin cancer is very threatening to health. Proper diagnosis of melanoma at an earlier stage is crucial for the success rate of complete cure. Dermoscopic images with Benign and malignant forms of skin cancer can be analyzed by computer vision system to streamline the process of skin cancer detection. In this study, we experimented with various neural networks which employ recent deep learning based models like PNASNet-5-Large, InceptionResNetV2, SENet154, InceptionV4. Dermoscopic images are properly processed and augmented before feeding them into the network. We tested our methods on International Skin Imaging Collaboration (ISIC) 2018 challenge dataset. Our system has achieved best validation score of 0.76 for PNASNet-5-Large model. Further improvement and optimization of the proposed methods with a bigger training dataset and carefully chosen hyper-parameter could improve the performances. The code available for download at https://github.com/miltonbd/ISIC_2018_classification |
| Tasks | Skin Lesion Classification |
| Published | 2019-01-30 |
| URL | http://arxiv.org/abs/1901.10802v1 |
| http://arxiv.org/pdf/1901.10802v1.pdf | |
| PWC | https://paperswithcode.com/paper/automated-skin-lesion-classification-using |
| Repo | |
| Framework | |
Mapping solar array location, size, and capacity using deep learning and overhead imagery
| Title | Mapping solar array location, size, and capacity using deep learning and overhead imagery |
| Authors | Jordan M. Malof, Boning Li, Bohao Huang, Kyle Bradbury, Artem Stretslov |
| Abstract | The effective integration of distributed solar photovoltaic (PV) arrays into existing power grids will require access to high quality data; the location, power capacity, and energy generation of individual solar PV installations. Unfortunately, existing methods for obtaining this data are limited in their spatial resolution and completeness. We propose a general framework for accurately and cheaply mapping individual PV arrays, and their capacities, over large geographic areas. At the core of this approach is a deep learning algorithm called SolarMapper - which we make publicly available - that can automatically map PV arrays in high resolution overhead imagery. We estimate the performance of SolarMapper on a large dataset of overhead imagery across three US cities in California. We also describe a procedure for deploying SolarMapper to new geographic regions, so that it can be utilized by others. We demonstrate the effectiveness of the proposed deployment procedure by using it to map solar arrays across the entire US state of Connecticut (CT). Using these results, we demonstrate that we achieve highly accurate estimates of total installed PV capacity within each of CT’s 168 municipal regions. |
| Tasks | |
| Published | 2019-02-28 |
| URL | http://arxiv.org/abs/1902.10895v1 |
| http://arxiv.org/pdf/1902.10895v1.pdf | |
| PWC | https://paperswithcode.com/paper/mapping-solar-array-location-size-and |
| Repo | |
| Framework | |
Robust Learning at Noisy Labeled Medical Images: Applied to Skin Lesion Classification
| Title | Robust Learning at Noisy Labeled Medical Images: Applied to Skin Lesion Classification |
| Authors | Cheng Xue, Qi Dou, Xueying Shi, Hao Chen, Pheng Ann Heng |
| Abstract | Deep neural networks (DNNs) have achieved great success in a wide variety of medical image analysis tasks. However, these achievements indispensably rely on the accurately-annotated datasets. If with the noisy-labeled images, the training procedure will immediately encounter difficulties, leading to a suboptimal classifier. This problem is even more crucial in the medical field, given that the annotation quality requires great expertise. In this paper, we propose an effective iterative learning framework for noisy-labeled medical image classification, to combat the lacking of high quality annotated medical data. Specifically, an online uncertainty sample mining method is proposed to eliminate the disturbance from noisy-labeled images. Next, we design a sample re-weighting strategy to preserve the usefulness of correctly-labeled hard samples. Our proposed method is validated on skin lesion classification task, and achieved very promising results. |
| Tasks | Image Classification, Skin Lesion Classification |
| Published | 2019-01-23 |
| URL | http://arxiv.org/abs/1901.07759v2 |
| http://arxiv.org/pdf/1901.07759v2.pdf | |
| PWC | https://paperswithcode.com/paper/robust-learning-at-noisy-labeled-medical |
| Repo | |
| Framework | |
A Discriminative Neural Model for Cross-Lingual Word Alignment
| Title | A Discriminative Neural Model for Cross-Lingual Word Alignment |
| Authors | Elias Stengel-Eskin, Tzu-Ray Su, Matt Post, Benjamin Van Durme |
| Abstract | We introduce a novel discriminative word alignment model, which we integrate into a Transformer-based machine translation model. In experiments based on a small number of labeled examples (~1.7K-5K sentences) we evaluate its performance intrinsically on both English-Chinese and English-Arabic alignment, where we achieve major improvements over unsupervised baselines (11-27 F1). We evaluate the model extrinsically on data projection for Chinese NER, showing that our alignments lead to higher performance when used to project NER tags from English to Chinese. Finally, we perform an ablation analysis and an annotation experiment that jointly support the utility and feasibility of future manual alignment elicitation. |
| Tasks | Machine Translation, Word Alignment |
| Published | 2019-09-01 |
| URL | https://arxiv.org/abs/1909.00444v1 |
| https://arxiv.org/pdf/1909.00444v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-discriminative-neural-model-for-cross |
| Repo | |
| Framework | |
Zero-shot Image Recognition Using Relational Matching, Adaptation and Calibration
| Title | Zero-shot Image Recognition Using Relational Matching, Adaptation and Calibration |
| Authors | Debasmit Das, C. S. George Lee |
| Abstract | Zero-shot learning (ZSL) for image classification focuses on recognizing novel categories that have no labeled data available for training. The learning is generally carried out with the help of mid-level semantic descriptors associated with each class. This semantic-descriptor space is generally shared by both seen and unseen categories. However, ZSL suffers from hubness, domain discrepancy and biased-ness towards seen classes. To tackle these problems, we propose a three-step approach to zero-shot learning. Firstly, a mapping is learned from the semantic-descriptor space to the image-feature space. This mapping learns to minimize both one-to-one and pairwise distances between semantic embeddings and the image features of the corresponding classes. Secondly, we propose test-time domain adaptation to adapt the semantic embedding of the unseen classes to the test data. This is achieved by finding correspondences between the semantic descriptors and the image features. Thirdly, we propose scaled calibration on the classification scores of the seen classes. This is necessary because the ZSL model is biased towards seen classes as the unseen classes are not used in the training. Finally, to validate the proposed three-step approach, we performed experiments on four benchmark datasets where the proposed method outperformed previous results. We also studied and analyzed the performance of each component of our proposed ZSL framework. |
| Tasks | Calibration, Domain Adaptation, Image Classification, Zero-Shot Learning |
| Published | 2019-03-27 |
| URL | http://arxiv.org/abs/1903.11701v1 |
| http://arxiv.org/pdf/1903.11701v1.pdf | |
| PWC | https://paperswithcode.com/paper/zero-shot-image-recognition-using-relational |
| Repo | |
| Framework | |
ElimiNet: A Model for Eliminating Options for Reading Comprehension with Multiple Choice Questions
| Title | ElimiNet: A Model for Eliminating Options for Reading Comprehension with Multiple Choice Questions |
| Authors | Soham Parikh, Ananya B. Sai, Preksha Nema, Mitesh M. Khapra |
| Abstract | The task of Reading Comprehension with Multiple Choice Questions, requires a human (or machine) to read a given passage, question pair and select one of the n given options. The current state of the art model for this task first computes a question-aware representation for the passage and then selects the option which has the maximum similarity with this representation. However, when humans perform this task they do not just focus on option selection but use a combination of elimination and selection. Specifically, a human would first try to eliminate the most irrelevant option and then read the passage again in the light of this new information (and perhaps ignore portions corresponding to the eliminated option). This process could be repeated multiple times till the reader is finally ready to select the correct option. We propose ElimiNet, a neural network-based model which tries to mimic this process. Specifically, it has gates which decide whether an option can be eliminated given the passage, question pair and if so it tries to make the passage representation orthogonal to this eliminated option (akin to ignoring portions of the passage corresponding to the eliminated option). The model makes multiple rounds of partial elimination to refine the passage representation and finally uses a selection module to pick the best option. We evaluate our model on the recently released large scale RACE dataset and show that it outperforms the current state of the art model on 7 out of the $13$ question types in this dataset. Further, we show that taking an ensemble of our elimination-selection based method with a selection based method gives us an improvement of 3.1% over the best-reported performance on this dataset. |
| Tasks | Reading Comprehension |
| Published | 2019-04-04 |
| URL | http://arxiv.org/abs/1904.02651v1 |
| http://arxiv.org/pdf/1904.02651v1.pdf | |
| PWC | https://paperswithcode.com/paper/eliminet-a-model-for-eliminating-options-for-1 |
| Repo | |
| Framework | |
