January 25, 2020

3154 words 15 mins read

Paper Group ANR 1710

A Computer Vision Application for Assessing Facial Acne Severity from Selfie Images. Multi-task human analysis in still images: 2D/3D pose, depth map, and multi-part segmentation. Supervised Negative Binomial Classifier for Probabilistic Record Linkage. Validating Weak-form Market Efficiency in United States Stock Markets with Trend Deterministic P …

A Computer Vision Application for Assessing Facial Acne Severity from Selfie Images


Title	A Computer Vision Application for Assessing Facial Acne Severity from Selfie Images
Authors	Tingting Zhao, Hang Zhang, Jacob Spoelstra
Abstract	We worked with Nestle SHIELD (Skin Health, Innovation, Education, and Longevity Development, NSH) to develop a deep learning model that is able to assess acne severity from selfie images as accurate as dermatologists. The model was deployed as a mobile application, providing patients an easy way to assess and track the progress of their acne treatment. NSH acquired 4,700 selfie images for this study and recruited 11 internal dermatologists to label them in five categories: 1-Clear, 2- Almost Clear, 3-Mild, 4-Moderate, 5-Severe. Using OpenCV to detect facial landmarks we cut specific skin patches from the selfie images in order to minimize irrelevant background. We then applied a transfer learning approach by extracting features from the patches using a ResNet 152 pre-trained model, followed by a fully connected layer trained to approximate the desired severity rating. To address the problem of spatial sensitivity of CNN models, we introduce a new image rolling data augmentation approach, effectively causing acne lesions appeared in more locations in the training images. Our results demonstrate that this approach improved the generalization of the CNN model, outperforming more than half of the panel of human dermatologists on test images. To our knowledge, this is the first deep learning-based solution for acne assessment using selfie images.
Tasks	Data Augmentation, Transfer Learning
Published	2019-07-18
URL	https://arxiv.org/abs/1907.07901v3
PDF	https://arxiv.org/pdf/1907.07901v3.pdf
PWC	https://paperswithcode.com/paper/a-computer-vision-application-for-assessing
Repo
Framework

Multi-task human analysis in still images: 2D/3D pose, depth map, and multi-part segmentation


Title	Multi-task human analysis in still images: 2D/3D pose, depth map, and multi-part segmentation
Authors	Daniel Sánchez, Marc Oliu, Meysam Madadi, Xavier Baró, Sergio Escalera
Abstract	While many individual tasks in the domain of human analysis have recently received an accuracy boost from deep learning approaches, multi-task learning has mostly been ignored due to a lack of data. New synthetic datasets are being released, filling this gap with synthetic generated data. In this work, we analyze four related human analysis tasks in still images in a multi-task scenario by leveraging such datasets. Specifically, we study the correlation of 2D/3D pose estimation, body part segmentation and full-body depth estimation. These tasks are learned via the well-known Stacked Hourglass module such that each of the task-specific streams shares information with the others. The main goal is to analyze how training together these four related tasks can benefit each individual task for a better generalization. Results on the newly released SURREAL dataset show that all four tasks benefit from the multi-task approach, but with different combinations of tasks: while combining all four tasks improves 2D pose estimation the most, 2D pose improves neither 3D pose nor full-body depth estimation. On the other hand 2D parts segmentation can benefit from 2D pose but not from 3D pose. In all cases, as expected, the maximum improvement is achieved on those human body parts that show more variability in terms of spatial distribution, appearance and shape, e.g. wrists and ankles.
Tasks	3D Pose Estimation, Depth Estimation, Multi-Task Learning, Pose Estimation
Published	2019-05-08
URL	https://arxiv.org/abs/1905.03003v1
PDF	https://arxiv.org/pdf/1905.03003v1.pdf
PWC	https://paperswithcode.com/paper/multi-task-human-analysis-in-still-images
Repo
Framework

Supervised Negative Binomial Classifier for Probabilistic Record Linkage


Title	Supervised Negative Binomial Classifier for Probabilistic Record Linkage
Authors	Harish Kashyap K, Kiran Byadarhaly, Saumya Shah
Abstract	Motivated by the need of the linking records across various databases, we propose a novel graphical model based classifier that uses a mixture of Poisson distributions with latent variables. The idea is to derive insight into each pair of hypothesis records that match by inferring its underlying latent rate of error using Bayesian Modeling techniques. The novel approach of using gamma priors for learning the latent variables along with supervised labels is unique and allows for active learning. The naive assumption is made deliberately as to the independence of the fields to propose a generalized theory for this class of problems and not to undermine the hierarchical dependencies that could be present in different scenarios. This classifier is able to work with sparse and streaming data. The application to record linkage is able to meet several challenges of sparsity, data streams and varying nature of the data-sets.
Tasks	Active Learning
Published	2019-08-11
URL	https://arxiv.org/abs/1908.03830v1
PDF	https://arxiv.org/pdf/1908.03830v1.pdf
PWC	https://paperswithcode.com/paper/supervised-negative-binomial-classifier-for
Repo
Framework

Validating Weak-form Market Efficiency in United States Stock Markets with Trend Deterministic Price Data and Machine Learning


Title	Validating Weak-form Market Efficiency in United States Stock Markets with Trend Deterministic Price Data and Machine Learning
Authors	Samuel Showalter, Jeffrey Gropp
Abstract	The Efficient Market Hypothesis has been a staple of economics research for decades. In particular, weak-form market efficiency – the notion that past prices cannot predict future performance – is strongly supported by econometric evidence. In contrast, machine learning algorithms implemented to predict stock price have been touted, to varying degrees, as successful. Moreover, some data scientists boast the ability to garner above-market returns using price data alone. This study endeavors to connect existing econometric research on weak-form efficient markets with data science innovations in algorithmic trading. First, a traditional exploration of stationarity in stock index prices over the past decade is conducted with Augmented Dickey-Fuller and Variance Ratio tests. Then, an algorithmic trading platform is implemented with the use of five machine learning algorithms. Econometric findings identify potential stationarity, hinting technical evaluation may be possible, though algorithmic trading results find little predictive power in any machine learning model, even when using trend-specific metrics. Accounting for transaction costs and risk, no system achieved above-market returns consistently. Our findings reinforce the validity of weak-form market efficiency.
Tasks
Published	2019-09-11
URL	https://arxiv.org/abs/1909.05151v1
PDF	https://arxiv.org/pdf/1909.05151v1.pdf
PWC	https://paperswithcode.com/paper/validating-weak-form-market-efficiency-in
Repo
Framework

Zero-shot Text Classification With Generative Language Models


Title	Zero-shot Text Classification With Generative Language Models
Authors	Raul Puri, Bryan Catanzaro
Abstract	This work investigates the use of natural language to enable zero-shot model adaptation to new tasks. We use text and metadata from social commenting platforms as a source for a simple pretraining task. We then provide the language model with natural language descriptions of classification tasks as input and train it to generate the correct answer in natural language via a language modeling objective. This allows the model to generalize to new classification tasks without the need for multiple multitask classification heads. We show the zero-shot performance of these generative language models, trained with weak supervision, on six benchmark text classification datasets from the torchtext library. Despite no access to training data, we achieve up to a 45% absolute improvement in classification accuracy over random or majority class baselines. These results show that natural language can serve as simple and powerful descriptors for task adaptation. We believe this points the way to new metalearning strategies for text problems.
Tasks	Language Modelling, Text Classification
Published	2019-12-10
URL	https://arxiv.org/abs/1912.10165v1
PDF	https://arxiv.org/pdf/1912.10165v1.pdf
PWC	https://paperswithcode.com/paper/zero-shot-text-classification-with-generative
Repo
Framework

Automatic Discovery of Families of Network Generative Processes


Title	Automatic Discovery of Families of Network Generative Processes
Authors	Telmo Menezes, Camille Roth
Abstract	Designing plausible network models typically requires scholars to form a priori intuitions on the key drivers of network formation. Oftentimes, these intuitions are supported by the statistical estimation of a selection of network evolution processes which will form the basis of the model to be developed. Machine learning techniques have lately been introduced to assist the automatic discovery of generative models. These approaches may more broadly be described as “symbolic regression”, where fundamental network dynamic functions, rather than just parameters, are evolved through genetic programming. This chapter first aims at reviewing the principles, efforts and the emerging literature in this direction, which is very much aligned with the idea of creating artificial scientists. Our contribution then aims more specifically at building upon an approach recently developed by us [Menezes & Roth, 2014] in order to demonstrate the existence of families of networks that may be described by similar generative processes. In other words, symbolic regression may be used to group networks according to their inferred genotype (in terms of generative processes) rather than their observed phenotype (in terms of statistical/topological features). Our empirical case is based on an original data set of 238 anonymized ego-centered networks of Facebook friends, further yielding insights on the formation of sociability networks.
Tasks
Published	2019-06-26
URL	https://arxiv.org/abs/1906.12332v1
PDF	https://arxiv.org/pdf/1906.12332v1.pdf
PWC	https://paperswithcode.com/paper/automatic-discovery-of-families-of-network
Repo
Framework

A Unified Algebraic Framework for Non-Monotonicity


Title	A Unified Algebraic Framework for Non-Monotonicity
Authors	Nourhan Ehab, Haythem O. Ismail
Abstract	Tremendous research effort has been dedicated over the years to thoroughly investigate non-monotonic reasoning. With the abundance of non-monotonic logical formalisms, a unified theory that enables comparing the different approaches is much called for. In this paper, we present an algebraic graded logic we refer to as LogAG capable of encompassing a wide variety of non-monotonic formalisms. We build on Lin and Shoham’s argument systems first developed to formalize non-monotonic commonsense reasoning. We show how to encode argument systems as LogAG theories, and prove that LogAG captures the notion of belief spaces in argument systems. Since argument systems capture default logic, autoepistemic logic, the principle of negation as failure, and circumscription, our results show that LogAG captures the before-mentioned non-monotonic logical formalisms as well. Previous results show that LogAG subsumes possibilistic logic and any non-monotonic inference relation satisfying Makinson’s rationality postulates. In this way, LogAG provides a powerful unified framework for non-monotonicity.
Tasks
Published	2019-07-22
URL	https://arxiv.org/abs/1907.09103v1
PDF	https://arxiv.org/pdf/1907.09103v1.pdf
PWC	https://paperswithcode.com/paper/a-unified-algebraic-framework-for-non
Repo
Framework

Evaluation of Transfer Learning for Classification of: (1) Diabetic Retinopathy by Digital Fundus Photography and (2) Diabetic Macular Edema, Choroidal Neovascularization and Drusen by Optical Coherence Tomography


Title	Evaluation of Transfer Learning for Classification of: (1) Diabetic Retinopathy by Digital Fundus Photography and (2) Diabetic Macular Edema, Choroidal Neovascularization and Drusen by Optical Coherence Tomography
Authors	Rony Gelman
Abstract	Deep learning has been successfully applied to a variety of image classification tasks. There has been keen interest to apply deep learning in the medical domain, particularly specialties that heavily utilize imaging, such as ophthalmology. One issue that may hinder application of deep learning to the medical domain is the vast amount of data necessary to train deep neural networks (DNNs). Because of regulatory and privacy issues associated with medicine, and the generally proprietary nature of data in medical domains, obtaining large datasets to train DNNs is a challenge, particularly in the ophthalmology domain. Transfer learning is a technique developed to address the issue of applying DNNs for domains with limited data. Prior reports on transfer learning have examined custom networks to fully train or used a particular DNN for transfer learning. However, to the best of my knowledge, no work has systematically examined a suite of DNNs for transfer learning for classification of diabetic retinopathy, diabetic macular edema, and two key features of age-related macular degeneration. This work attempts to investigate transfer learning for classification of these ophthalmic conditions. Part I gives a condensed overview of neural networks and the DNNs under evaluation. Part II gives the reader the necessary background concerning diabetic retinopathy and prior work on classification using retinal fundus photographs. The methodology and results of transfer learning for diabetic retinopathy classification are presented, showing that transfer learning towards this domain is feasible, with promising accuracy. Part III gives an overview of diabetic macular edema, choroidal neovascularization and drusen (features associated with age-related macular degeneration), and presents results for transfer learning evaluation using optical coherence tomography to classify these entities.
Tasks	Image Classification, Transfer Learning
Published	2019-01-26
URL	http://arxiv.org/abs/1902.04151v1
PDF	http://arxiv.org/pdf/1902.04151v1.pdf
PWC	https://paperswithcode.com/paper/evaluation-of-transfer-learning-for
Repo
Framework

Low-Complexity LSTM-Assisted Bit-Flipping Algorithm for Successive Cancellation List Polar Decoder


Title	Low-Complexity LSTM-Assisted Bit-Flipping Algorithm for Successive Cancellation List Polar Decoder
Authors	Chun-Hsiang Chen, Chieh-Fang Teng, An-Yeu Wu
Abstract	Polar codes have attracted much attention in the past decade due to their capacity-achieving performance. The higher decoding capacity is required for 5G and beyond 5G (B5G). Although the cyclic redundancy check (CRC)- assisted successive cancellation list bit-flipping (CA-SCLF) decoders have been developed to obtain a better performance, the solution to error bit correction (bit-flipping) problem is still imperfect and hard to design. In this work, we leverage the expert knowledge in communication systems and adopt deep learning (DL) technique to obtain the better solution. A low-complexity long short-term memory network (LSTM)-assisted CA-SCLF decoder is proposed to further improve the performance of conventional CA-SCLF and avoid complexity and memory overhead. Our test results show that we can effectively improve the BLER performance by 0.11dB compared to prior work and reduce the complexity and memory overhead by over 30% of the network.
Tasks
Published	2019-12-11
URL	https://arxiv.org/abs/1912.05158v1
PDF	https://arxiv.org/pdf/1912.05158v1.pdf
PWC	https://paperswithcode.com/paper/low-complexity-lstm-assisted-bit-flipping
Repo
Framework

Word-level Speech Recognition with a Dynamic Lexicon


Title	Word-level Speech Recognition with a Dynamic Lexicon
Authors	Ronan Collobert, Awni Hannun, Gabriel Synnaeve
Abstract	We propose a direct-to-word sequence model with a dynamic lexicon. Our word network constructs word embeddings dynamically from the character level tokens. The word network can be integrated seamlessly with arbitrary sequence models including Connectionist Temporal Classification and encoder-decoder models with attention. Sub-word units are commonly used in speech recognition yet are generated without the use of acoustic context. We show our direct-to-word model can achieve word error rate gains over sub-word level models for speech recognition. Furthermore, we empirically validate that the word-level embeddings we learn contain significant acoustic information, making them more suitable for use in speech recognition. We also show that our direct-to-word approach retains the ability to predict words not seen at training time without any retraining.
Tasks	Speech Recognition, Word Embeddings
Published	2019-06-10
URL	https://arxiv.org/abs/1906.04323v1
PDF	https://arxiv.org/pdf/1906.04323v1.pdf
PWC	https://paperswithcode.com/paper/word-level-speech-recognition-with-a-dynamic
Repo
Framework

Reading the Manual: Event Extraction as Definition Comprehension


Title	Reading the Manual: Event Extraction as Definition Comprehension
Authors	Yunmo Chen, Tongfei Chen, Seth Ebner, Benjamin Van Durme
Abstract	We propose a novel approach to event extraction that supplies models with \emph{bleached statements}: machine-readable natural language sentences that are based on annotation guidelines and that describe generic occurrences of events. We introduce a model that incrementally replaces the bleached arguments in a statement with responses obtained by querying text with the statement itself. Experimental results demonstrate that our model is able to extract events under closed ontologies and can generalize to unseen event types simply by reading new bleached statements.
Tasks
Published	2019-12-03
URL	https://arxiv.org/abs/1912.01586v1
PDF	https://arxiv.org/pdf/1912.01586v1.pdf
PWC	https://paperswithcode.com/paper/reading-the-manual-event-extraction-as
Repo
Framework

Un modèle Bayésien de co-clustering de données mixtes


Title	Un modèle Bayésien de co-clustering de données mixtes
Authors	Aichetou Bouchareb, Marc Boullé, Fabrice Rossi, Fabrice Clérot
Abstract	We propose a MAP Bayesian approach to perform and evaluate a co-clustering of mixed-type data tables. The proposed model infers an optimal segmentation of all variables then performs a co-clustering by minimizing a Bayesian model selection cost function. One advantage of this approach is that it is user parameter-free. Another main advantage is the proposed criterion which gives an exact measure of the model quality, measured by probability of fitting it to the data. Continuous optimization of this criterion ensures finding better and better models while avoiding data over-fitting. The experiments conducted on real data show the interest of this co-clustering approach in exploratory data analysis of large data sets.
Tasks	Model Selection
Published	2019-02-06
URL	http://arxiv.org/abs/1902.02056v1
PDF	http://arxiv.org/pdf/1902.02056v1.pdf
PWC	https://paperswithcode.com/paper/un-modele-bayesien-de-co-clustering-de
Repo
Framework

Out of the Box: A combined approach for handling occlusion in Human Pose Estimation


Title	Out of the Box: A combined approach for handling occlusion in Human Pose Estimation
Authors	Rohit Jena
Abstract	Human Pose estimation is a challenging problem, especially in the case of 3D pose estimation from 2D images due to many different factors like occlusion, depth ambiguities, intertwining of people, and in general crowds. 2D multi-person human pose estimation in the wild also suffers from the same problems - occlusion, ambiguities, and disentanglement of people’s body parts. Being a fundamental problem with loads of applications, including but not limited to surveillance, economical motion capture for video games and movies, and physiotherapy, this is an interesting problem to be solved both from a practical perspective and from an intellectual perspective as well. Although there are cases where no pose estimation can ever predict with 100% accuracy (cases where even humans would fail), there are several algorithms that have brought new state-of-the-art performance in human pose estimation in the wild. We look at a few algorithms with different approaches and also formulate our own approach to tackle a consistently bugging problem, i.e. occlusions.
Tasks	3D Pose Estimation, Motion Capture, Pose Estimation
Published	2019-04-25
URL	http://arxiv.org/abs/1904.11157v1
PDF	http://arxiv.org/pdf/1904.11157v1.pdf
PWC	https://paperswithcode.com/paper/out-of-the-box-a-combined-approach-for
Repo
Framework

Variational Information Distillation for Knowledge Transfer


Title	Variational Information Distillation for Knowledge Transfer
Authors	Sungsoo Ahn, Shell Xu Hu, Andreas Damianou, Neil D. Lawrence, Zhenwen Dai
Abstract	Transferring knowledge from a teacher neural network pretrained on the same or a similar task to a student neural network can significantly improve the performance of the student neural network. Existing knowledge transfer approaches match the activations or the corresponding hand-crafted features of the teacher and the student networks. We propose an information-theoretic framework for knowledge transfer which formulates knowledge transfer as maximizing the mutual information between the teacher and the student networks. We compare our method with existing knowledge transfer methods on both knowledge distillation and transfer learning tasks and show that our method consistently outperforms existing methods. We further demonstrate the strength of our method on knowledge transfer across heterogeneous network architectures by transferring knowledge from a convolutional neural network (CNN) to a multi-layer perceptron (MLP) on CIFAR-10. The resulting MLP significantly outperforms the-state-of-the-art methods and it achieves similar performance to the CNN with a single convolutional layer.
Tasks	Transfer Learning
Published	2019-04-11
URL	http://arxiv.org/abs/1904.05835v1
PDF	http://arxiv.org/pdf/1904.05835v1.pdf
PWC	https://paperswithcode.com/paper/variational-information-distillation-for
Repo
Framework

Scaling active inference


Title	Scaling active inference
Authors	Alexander Tschantz, Manuel Baltieri, Anil. K. Seth, Christopher L. Buckley
Abstract	In reinforcement learning (RL), agents often operate in partially observed and uncertain environments. Model-based RL suggests that this is best achieved by learning and exploiting a probabilistic model of the world. ‘Active inference’ is an emerging normative framework in cognitive and computational neuroscience that offers a unifying account of how biological agents achieve this. On this framework, inference, learning and action emerge from a single imperative to maximize the Bayesian evidence for a niched model of the world. However, implementations of this process have thus far been restricted to low-dimensional and idealized situations. Here, we present a working implementation of active inference that applies to high-dimensional tasks, with proof-of-principle results demonstrating efficient exploration and an order of magnitude increase in sample efficiency over strong model-free baselines. Our results demonstrate the feasibility of applying active inference at scale and highlight the operational homologies between active inference and current model-based approaches to RL.
Tasks	Efficient Exploration
Published	2019-11-24
URL	https://arxiv.org/abs/1911.10601v1
PDF	https://arxiv.org/pdf/1911.10601v1.pdf
PWC	https://paperswithcode.com/paper/scaling-active-inference
Repo
Framework