January 28, 2020

3298 words 16 mins read

Paper Group ANR 967

A Scalable Approach for Facial Action Unit Classifier Training UsingNoisy Data for Pre-Training. Patch Clustering for Representation of Histopathology Images. Optimal Attacks on Reinforcement Learning Policies. Policy Based Inference in Trick-Taking Card Games. Uncertainty Estimates for Ordinal Embeddings. Gradient Sparification for Asynchronous Di …

A Scalable Approach for Facial Action Unit Classifier Training UsingNoisy Data for Pre-Training


Title	A Scalable Approach for Facial Action Unit Classifier Training UsingNoisy Data for Pre-Training
Authors	Alberto Fung, Daniel McDuff
Abstract	Machine learning systems are being used to automate many types of laborious labeling tasks. Facial actioncoding is an example of such a labeling task that requires copious amounts of time and a beyond average level of human domain expertise. In recent years, the use of end-to-end deep neural networks has led to significant improvements in action unit recognition performance and many network architectures have been proposed. Do the more complex deep neural network(DNN) architectures perform sufficiently well to justify the additional complexity? We show that pre-training on a large diverse set of noisy data can result in even a simple CNN model improving over the current state-of-the-art DNN architectures.The average F1-score achieved with our proposed method on the DISFA dataset is 0.60, compared to a previous state-of-the-art of 0.57. Additionally, we show how the number of subjects and number of images used for pre-training impacts the model performance. The approach that we have outlined is open-source, highly scalable, and not dependent on the model architecture. We release the code and data: https://github.com/facialactionpretrain/facs.
Tasks
Published	2019-11-14
URL	https://arxiv.org/abs/1911.05946v1
PDF	https://arxiv.org/pdf/1911.05946v1.pdf
PWC	https://paperswithcode.com/paper/a-scalable-approach-for-facial-action-unit
Repo
Framework

Patch Clustering for Representation of Histopathology Images


Title	Patch Clustering for Representation of Histopathology Images
Authors	Wafa Chenni, Habib Herbi, Morteza Babaie, H. R. Tizhoosh
Abstract	Whole Slide Imaging (WSI) has become an important topic during the last decade. Even though significant progress in both medical image processing and computational resources has been achieved, there are still problems in WSI that need to be solved. A major challenge is the scan size. The dimensions of digitized tissue samples may exceed 100,000 by 100,000 pixels causing memory and efficiency obstacles for real-time processing. The main contribution of this work is representing a WSI by selecting a small number of patches for algorithmic processing (e.g., indexing and search). As a result, we reduced the search time and storage by various factors between ($50% - 90%$), while losing only a few percentages in the patch retrieval accuracy. A self-organizing map (SOM) has been applied on local binary patterns (LBP) and deep features of the KimiaPath24 dataset in order to cluster patches that share the same characteristics. We used a Gaussian mixture model (GMM) to represent each class with a rather small ($10%-50%$) portion of patches. The results showed that LBP features can outperform deep features. By selecting only $50%$ of all patches after SOM clustering and GMM patch selection, we received $65%$ accuracy for retrieval of the best match, while the maximum accuracy (using all patches) was $69%$.
Tasks
Published	2019-03-17
URL	http://arxiv.org/abs/1903.07013v1
PDF	http://arxiv.org/pdf/1903.07013v1.pdf
PWC	https://paperswithcode.com/paper/patch-clustering-for-representation-of
Repo
Framework

Optimal Attacks on Reinforcement Learning Policies


Title	Optimal Attacks on Reinforcement Learning Policies
Authors	Alessio Russo, Alexandre Proutiere
Abstract	Control policies, trained using the Deep Reinforcement Learning, have been recently shown to be vulnerable to adversarial attacks introducing even very small perturbations to the policy input. The attacks proposed so far have been designed using heuristics, and build on existing adversarial example crafting techniques used to dupe classifiers in supervised learning. In contrast, this paper investigates the problem of devising optimal attacks, depending on a well-defined attacker’s objective, e.g., to minimize the main agent average reward. When the policy and the system dynamics, as well as rewards, are known to the attacker, a scenario referred to as a white-box attack, designing optimal attacks amounts to solving a Markov Decision Process. For what we call black-box attacks, where neither the policy nor the system is known, optimal attacks can be trained using Reinforcement Learning techniques. Through numerical experiments, we demonstrate the efficiency of our attacks compared to existing attacks (usually based on Gradient methods). We further quantify the potential impact of attacks and establish its connection to the smoothness of the policy under attack. Smooth policies are naturally less prone to attacks (this explains why Lipschitz policies, with respect to the state, are more resilient). Finally, we show that from the main agent perspective, the system uncertainties and the attacker can be modeled as a Partially Observable Markov Decision Process. We actually demonstrate that using Reinforcement Learning techniques tailored to POMDP (e.g. using Recurrent Neural Networks) leads to more resilient policies.
Tasks
Published	2019-07-31
URL	https://arxiv.org/abs/1907.13548v1
PDF	https://arxiv.org/pdf/1907.13548v1.pdf
PWC	https://paperswithcode.com/paper/optimal-attacks-on-reinforcement-learning
Repo
Framework

Policy Based Inference in Trick-Taking Card Games


Title	Policy Based Inference in Trick-Taking Card Games
Authors	Douglas Rebstock, Christopher Solinas, Michael Buro, Nathan R. Sturtevant
Abstract	Trick-taking card games feature a large amount of private information that slowly gets revealed through a long sequence of actions. This makes the number of histories exponentially large in the action sequence length, as well as creating extremely large information sets. As a result, these games become too large to solve. To deal with these issues many algorithms employ inference, the estimation of the probability of states within an information set. In this paper, we demonstrate a Policy Based Inference (PI) algorithm that uses player modelling to infer the probability we are in a given state. We perform experiments in the German trick-taking card game Skat, in which we show that this method vastly improves the inference as compared to previous work, and increases the performance of the state-of-the-art Skat AI system Kermit when it is employed into its determinized search algorithm.
Tasks	Card Games
Published	2019-05-27
URL	https://arxiv.org/abs/1905.10911v1
PDF	https://arxiv.org/pdf/1905.10911v1.pdf
PWC	https://paperswithcode.com/paper/policy-based-inference-in-trick-taking-card
Repo
Framework

Uncertainty Estimates for Ordinal Embeddings


Title	Uncertainty Estimates for Ordinal Embeddings
Authors	Michael Lohaus, Philipp Hennig, Ulrike von Luxburg
Abstract	To investigate objects without a describable notion of distance, one can gather ordinal information by asking triplet comparisons of the form “Is object $x$ closer to $y$ or is $x$ closer to $z$?” In order to learn from such data, the objects are typically embedded in a Euclidean space while satisfying as many triplet comparisons as possible. In this paper, we introduce empirical uncertainty estimates for standard embedding algorithms when few noisy triplets are available, using a bootstrap and a Bayesian approach. In particular, simulations show that these estimates are well calibrated and can serve to select embedding parameters or to quantify uncertainty in scientific applications.
Tasks
Published	2019-06-27
URL	https://arxiv.org/abs/1906.11655v1
PDF	https://arxiv.org/pdf/1906.11655v1.pdf
PWC	https://paperswithcode.com/paper/uncertainty-estimates-for-ordinal-embeddings
Repo
Framework

Gradient Sparification for Asynchronous Distributed Training


Title	Gradient Sparification for Asynchronous Distributed Training
Authors	Zijie Yan
Abstract	Modern large scale machine learning applications require stochastic optimization algorithms to be implemented on distributed computational architectures. A key bottleneck is the communication overhead for exchanging information, such as stochastic gradients, among different nodes. Recently, gradient sparsification techniques have been proposed to reduce communications cost and thus alleviate the network overhead. However, most of gradient sparsification techniques consider only synchronous parallelism and cannot be applied in asynchronous scenarios, such as asynchronous distributed training for federated learning at mobile devices. In this paper, we present a dual-way gradient sparsification approach (DGS) that is suitable for asynchronous distributed training. We let workers download model difference, instead of the global model, from the server, and the model difference information is also sparsified so that the information exchanged overhead is reduced by sparsifying the dual-way communication between the server and workers. To preserve accuracy under dual-way sparsification, we design a sparsification aware momentum (SAMomentum) to turn sparsification into adaptive batch size between each parameter. We conduct experiments at a cluster of 32 workers, and the results show that, with the same compression ratio but much lower communication cost, our approach can achieve better scalability and generalization ability.
Tasks	Stochastic Optimization
Published	2019-10-24
URL	https://arxiv.org/abs/1910.10929v1
PDF	https://arxiv.org/pdf/1910.10929v1.pdf
PWC	https://paperswithcode.com/paper/gradient-sparification-for-asynchronous
Repo
Framework

Focus on What’s Informative and Ignore What’s not: Communication Strategies in a Referential Game


Title	Focus on What’s Informative and Ignore What’s not: Communication Strategies in a Referential Game
Authors	Roberto Dessì, Diane Bouchacourt, Davide Crepaldi, Marco Baroni
Abstract	Research in multi-agent cooperation has shown that artificial agents are able to learn to play a simple referential game while developing a shared lexicon. This lexicon is not easy to analyze, as it does not show many properties of a natural language. In a simple referential game with two neural network-based agents, we analyze the object-symbol mapping trying to understand what kind of strategy was used to develop the emergent language. We see that, when the environment is uniformly distributed, the agents rely on a random subset of features to describe the objects. When we modify the objects making one feature non-uniformly distributed,the agents realize it is less informative and start to ignore it, and, surprisingly, they make a better use of the remaining features. This interesting result suggests that more natural, less uniformly distributed environments might aid in spurring the emergence of better-behaved languages.
Tasks
Published	2019-11-05
URL	https://arxiv.org/abs/1911.01892v1
PDF	https://arxiv.org/pdf/1911.01892v1.pdf
PWC	https://paperswithcode.com/paper/focus-on-whats-informative-and-ignore-whats
Repo
Framework


Title	Evaluation of a deep learning system for the joint automated detection of diabetic retinopathy and age-related macular degeneration
Authors	Cristina González-Gonzalo, Verónica Sánchez-Gutiérrez, Paula Hernández-Martínez, Inés Contreras, Yara T. Lechanteur, Artin Domanian, Bram van Ginneken, Clara I. Sánchez
Abstract	Purpose: To validate the performance of a commercially-available, CE-certified deep learning (DL) system, RetCAD v.1.3.0 (Thirona, Nijmegen, The Netherlands), for the joint automatic detection of diabetic retinopathy (DR) and age-related macular degeneration (AMD) in color fundus (CF) images on a dataset with mixed presence of eye diseases. Methods: Evaluation of joint detection of referable DR and AMD was performed on a DR-AMD dataset with 600 images acquired during routine clinical practice, containing referable and non-referable cases of both diseases. Each image was graded for DR and AMD by an experienced ophthalmologist to establish the reference standard (RS), and by four independent observers for comparison with human performance. Validation was furtherly assessed on Messidor (1200 images) for individual identification of referable DR, and the Age-Related Eye Disease Study (AREDS) dataset (133821 images) for referable AMD, against the corresponding RS. Results: Regarding joint validation on the DR-AMD dataset, the system achieved an area under the ROC curve (AUC) of 95.1% for detection of referable DR (SE=90.1%, SP=90.6%). For referable AMD, the AUC was 94.9% (SE=91.8%, SP=87.5%). Average human performance for DR was SE=61.5% and SP=97.8%; for AMD, SE=76.5% and SP=96.1%. Regarding detection of referable DR in Messidor, AUC was 97.5% (SE=92.0%, SP=92.1%); for referable AMD in AREDS, AUC was 92.7% (SE=85.8%, SP=86.0%). Conclusions: The validated system performs comparably to human experts at simultaneous detection of DR and AMD. This shows that DL systems can facilitate access to joint screening of eye diseases and become a quick and reliable support for ophthalmological experts.
Tasks
Published	2019-03-22
URL	http://arxiv.org/abs/1903.09555v1
PDF	http://arxiv.org/pdf/1903.09555v1.pdf
PWC	https://paperswithcode.com/paper/evaluation-of-a-deep-learning-system-for-the
Repo
Framework

Augmented Data Science: Towards Industrialization and Democratization of Data Science


Title	Augmented Data Science: Towards Industrialization and Democratization of Data Science
Authors	Huseyin Uzunalioglu, Jin Cao, Chitra Phadke, Gerald Lehmann, Ahmet Akyamac, Ran He, Jeongran Lee, Maria Able
Abstract	Conversion of raw data into insights and knowledge requires substantial amounts of effort from data scientists. Despite breathtaking advances in Machine Learning (ML) and Artificial Intelligence (AI), data scientists still spend the majority of their effort in understanding and then preparing the raw data for ML/AI. The effort is often manual and ad hoc, and requires some level of domain knowledge. The complexity of the effort increases dramatically when data diversity, both in form and context, increases. In this paper, we introduce our solution, Augmented Data Science (ADS), towards addressing this “human bottleneck” in creating value from diverse datasets. ADS is a data-driven approach and relies on statistics and ML to extract insights from any data set in a domain-agnostic way to facilitate the data science process. Key features of ADS are the replacement of rudimentary data exploration and processing steps with automation and the augmentation of data scientist judgment with automatically-generated insights. We present building blocks of our end-to-end solution and provide a case study to exemplify its capabilities.
Tasks
Published	2019-09-12
URL	https://arxiv.org/abs/1909.05682v1
PDF	https://arxiv.org/pdf/1909.05682v1.pdf
PWC	https://paperswithcode.com/paper/augmented-data-science-towards
Repo
Framework

Structural characterization of musical harmonies


Title	Structural characterization of musical harmonies
Authors	Maria Rojo Gonz’alez, Simone Santini
Abstract	Understanding the structural characteristics of harmony is essential for an effective use of music as a communication medium. Of the three expressive axes of music (melody, rhythm, harmony), harmony is the foundation on which the emotional content is built, and its understanding is important in areas such as multimedia and affective computing. The common tool for studying this kind of structure in computing science is the formal grammar but, in the case of music, grammars run into problems due to the ambiguous nature of some of the concepts defined in music theory. In this paper, we consider one of such constructs: modulation, that is, the change of key in the middle of a musical piece, an important tool used by many authors to enhance the capacity of music to express emotions. We develop a hybrid method in which an evidence-gathering numerical method detects modulation and then, based on the detected tonalities, a non-ambiguous grammar can be used for analyzing the structure of each tonal component. Experiments with music from the XVII and XVIII centuries show that we can detect the precise point of modulation with an error of at most two chords in almost 97% of the cases. Finally, we show examples of complete modulation and structural analysis of musical harmonies.
Tasks
Published	2019-12-27
URL	https://arxiv.org/abs/1912.12362v1
PDF	https://arxiv.org/pdf/1912.12362v1.pdf
PWC	https://paperswithcode.com/paper/structural-characterization-of-musical
Repo
Framework

Pan-Private Uniformity Testing


Title	Pan-Private Uniformity Testing
Authors	Kareem Amin, Matthew Joseph, Jieming Mao
Abstract	A centrally differentially private algorithm maps raw data to differentially private outputs. In contrast, a locally differentially private algorithm may only access data through public interaction with data holders, and this interaction must be a differentially private function of the data. We study the intermediate model of pan-privacy. Unlike a locally private algorithm, a pan-private algorithm receives data in the clear. Unlike a centrally private algorithm, the algorithm receives data one element at a time and must maintain a differentially private internal state while processing this stream. First, we show that pan-privacy against multiple intrusions on the internal state is equivalent to sequentially interactive local privacy. Next, we contextualize pan-privacy against a single intrusion by analyzing the sample complexity of uniformity testing over domain $[k]$. Focusing on the dependence on $k$, centrally private uniformity testing has sample complexity $\Theta(\sqrt{k})$, while noninteractive locally private uniformity testing has sample complexity $\Theta(k)$. We show that the sample complexity of pan-private uniformity testing is $\Theta(k^{2/3})$. By a new $\Omega(k)$ lower bound for the sequentially interactive setting, we also separate pan-private from sequentially interactive locally private and multi-intrusion pan-private uniformity testing.
Tasks
Published	2019-11-04
URL	https://arxiv.org/abs/1911.01452v1
PDF	https://arxiv.org/pdf/1911.01452v1.pdf
PWC	https://paperswithcode.com/paper/pan-private-uniformity-testing
Repo
Framework

One-Shot Image-to-Image Translation via Part-Global Learning with a Multi-adversarial Framework


Title	One-Shot Image-to-Image Translation via Part-Global Learning with a Multi-adversarial Framework
Authors	Ziqiang Zheng, Zhibin Yu, Haiyong Zheng, Yang Yang, Heng Tao Shen
Abstract	It is well known that humans can learn and recognize objects effectively from several limited image samples. However, learning from just a few images is still a tremendous challenge for existing main-stream deep neural networks. Inspired by analogical reasoning in the human mind, a feasible strategy is to translate the abundant images of a rich source domain to enrich the relevant yet different target domain with insufficient image data. To achieve this goal, we propose a novel, effective multi-adversarial framework (MA) based on part-global learning, which accomplishes one-shot cross-domain image-to-image translation. In specific, we first devise a part-global adversarial training scheme to provide an efficient way for feature extraction and prevent discriminators being over-fitted. Then, a multi-adversarial mechanism is employed to enhance the image-to-image translation ability to unearth the high-level semantic representation. Moreover, a balanced adversarial loss function is presented, which aims to balance the training data and stabilize the training process. Extensive experiments demonstrate that the proposed approach can obtain impressive results on various datasets between two extremely imbalanced image domains and outperform state-of-the-art methods on one-shot image-to-image translation.
Tasks	Image-to-Image Translation, One Shot Image to Image Translation
Published	2019-05-12
URL	https://arxiv.org/abs/1905.04729v1
PDF	https://arxiv.org/pdf/1905.04729v1.pdf
PWC	https://paperswithcode.com/paper/one-shot-image-to-image-translation-via-part
Repo
Framework

Personalized Patent Claim Generation and Measurement


Title	Personalized Patent Claim Generation and Measurement
Authors	Jieh-Sheng Lee
Abstract	This work-in-progress paper proposes a framework to generate and measure personalized patent claims. The objective is to help inventors conceive better inventions by learning from relevant inventors. Patent claim generation is a way of “augmented inventing.” for inventors. Such patent claim generation leverages the recent transfer learning in the Deep Learning field, particularly the state-of-the-art Transformer-based models. In terms of system implementa-tion, it is planned to build an “auto-complete” function for patent claim drafting. The auto-complete function is analyzed from four different perspectives: extent of generation, generative direction, proximity of generation, and constraint in generation. Technically, the framework is composed of two Transformer models. One is for text generation and the other is for quality measurement. Specifically, the patent claim generation is based on GPT-2 model and the measurement of personalization is based on BERT model. The training data is inventor-centric and comes from the Inventors Endpoint API provided by the USPTO.
Tasks	Text Generation, Transfer Learning
Published	2019-12-07
URL	https://arxiv.org/abs/1912.03502v2
PDF	https://arxiv.org/pdf/1912.03502v2.pdf
PWC	https://paperswithcode.com/paper/personalized-patent-claim-generation-and
Repo
Framework

An Efficient Solution for Breast Tumor Segmentation and Classification in Ultrasound Images Using Deep Adversarial Learning


Title	An Efficient Solution for Breast Tumor Segmentation and Classification in Ultrasound Images Using Deep Adversarial Learning
Authors	Vivek Kumar Singh, Hatem A. Rashwan, Mohamed Abdel-Nasser, Md. Mostafa Kamal Sarker, Farhan Akram, Nidhi Pandey, Santiago Romani, Domenec Puig
Abstract	This paper proposes an efficient solution for tumor segmentation and classification in breast ultrasound (BUS) images. We propose to add an atrous convolution layer to the conditional generative adversarial network (cGAN) segmentation model to learn tumor features at different resolutions of BUS images. To automatically re-balance the relative impact of each of the highest level encoded features, we also propose to add a channel-wise weighting block in the network. In addition, the SSIM and L1-norm loss with the typical adversarial loss are used as a loss function to train the model. Our model outperforms the state-of-the-art segmentation models in terms of the Dice and IoU metrics, achieving top scores of 93.76% and 88.82%, respectively. In the classification stage, we show that few statistics features extracted from the shape of the boundaries of the predicted masks can properly discriminate between benign and malignant tumors with an accuracy of 85%$
Tasks
Published	2019-07-01
URL	https://arxiv.org/abs/1907.00887v1
PDF	https://arxiv.org/pdf/1907.00887v1.pdf
PWC	https://paperswithcode.com/paper/an-efficient-solution-for-breast-tumor
Repo
Framework


Title	Influence Maximization for Social Good: Use of Social Networks in Low Resource Communities
Authors	Amulya Yadav
Abstract	This thesis proposal makes the following technical contributions: (i) we provide a definition of the Dynamic Influence Maximization Under Uncertainty (or DIME) problem, which models the problem faced by homeless shelters accurately; (ii) we propose a novel Partially Observable Markov Decision Process (POMDP) model for solving the DIME problem; (iii) we design two scalable POMDP algorithms (PSINET and HEALER) for solving the DIME problem, since conventional POMDP solvers fail to scale up to sizes of interest; and (iv) we test our algorithms effectiveness in the real world by conducting a pilot study with actual homeless youth in Los Angeles. The success of this pilot (as explained later) shows the promise of using influence maximization for social good on a larger scale.
Tasks
Published	2019-12-03
URL	https://arxiv.org/abs/1912.02105v1
PDF	https://arxiv.org/pdf/1912.02105v1.pdf
PWC	https://paperswithcode.com/paper/influence-maximization-for-social-good-use-of
Repo
Framework