January 25, 2020

3209 words 16 mins read

Paper Group ANR 1718

Spiking Neural Predictive Coding for Continual Learning from Data Streams. Detecting gender differences in perception of emotion in crowdsourced data. Transfer of Temporal Logic Formulas in Reinforcement Learning. Towards High-fidelity Nonlinear 3D Face Morphable Model. Hierarchical Bayesian myocardial perfusion quantification. Research and applica …

Spiking Neural Predictive Coding for Continual Learning from Data Streams


Title	Spiking Neural Predictive Coding for Continual Learning from Data Streams
Authors	Alexander Ororbia
Abstract	For energy-efficient computation in specialized neuromorphic hardware, we present the Spiking Neural Coding Network, an instantiation of a family of artificial neural models strongly motivated by the theory of predictive coding. The model, in essence, works by operating in a never-ending process of “guess-and-check”, where neurons predict the activity values of one another and then immediately adjust their own activities to make better future predictions. The interactive, iterative nature of our neural system fits well into the continuous time formulation of data sensory stream prediction and, as we show, the model’s structure yields a simple, local synaptic update rule, which could be used to complement or replace online spike-timing dependent plasticity. In this article, we experiment with an instantiation of our model that consists of leaky integrate-and-fire units. However, the general framework within which our model is situated can naturally incorporate more complex, formal neurons such as the Hodgkin-Huxley model. Our experimental results in pattern recognition demonstrate the potential of the proposed model when binary spike trains are the primary paradigm for inter-neuron communication. Notably, our model is competitive in terms of classification performance, can conduct online semi-supervised learning, naturally experiences less forgetting when learning from a sequence of tasks, and is more computationally economical and biologically-plausible than popular artificial neural networks.
Tasks	Continual Learning
Published	2019-08-23
URL	https://arxiv.org/abs/1908.08655v2
PDF	https://arxiv.org/pdf/1908.08655v2.pdf
PWC	https://paperswithcode.com/paper/spiking-neural-predictive-coding-for
Repo
Framework

Detecting gender differences in perception of emotion in crowdsourced data


Title	Detecting gender differences in perception of emotion in crowdsourced data
Authors	Shahan Ali Memon, Hira Dhamyal, Oren Wright, Daniel Justice, Vijaykumar Palat, William Boler, Bhiksha Raj, Rita Singh
Abstract	Do men and women perceive emotions differently? Popular convictions place women as more emotionally perceptive than men. Empirical findings, however, remain inconclusive. Most prior studies focus on visual modalities. In addition, almost all of the studies are limited to experiments within controlled environments. Generalizability and scalability of these studies has not been sufficiently established. In this paper, we study the differences in perception of emotion between genders from speech data in the wild, annotated through crowdsourcing. While we limit ourselves to a single modality (i.e. speech), our framework is applicable to studies of emotion perception from all such loosely annotated data in general. Our paper addresses multiple serious challenges related to making statistically viable conclusions from crowdsourced data. Overall, the contributions of this paper are two fold: a reliable novel framework for perceptual studies from crowdsourced data; and the demonstration of statistically significant differences in speech-based emotion perception between genders.
Tasks
Published	2019-10-24
URL	https://arxiv.org/abs/1910.11386v4
PDF	https://arxiv.org/pdf/1910.11386v4.pdf
PWC	https://paperswithcode.com/paper/detecting-gender-differences-in-perception-of
Repo
Framework

Transfer of Temporal Logic Formulas in Reinforcement Learning


Title	Transfer of Temporal Logic Formulas in Reinforcement Learning
Authors	Zhe Xu, Ufuk Topcu
Abstract	Transferring high-level knowledge from a source task to a target task is an effective way to expedite reinforcement learning (RL). For example, propositional logic and first-order logic have been used as representations of such knowledge. We study the transfer of knowledge between tasks in which the timing of the events matters. We call such tasks temporal tasks. We concretize similarity between temporal tasks through a notion of logical transferability, and develop a transfer learning approach between different yet similar temporal tasks. We first propose an inference technique to extract metric interval temporal logic (MITL) formulas in sequential disjunctive normal form from labeled trajectories collected in RL of the two tasks. If logical transferability is identified through this inference, we construct a timed automaton for each sequential conjunctive subformula of the inferred MITL formulas from both tasks. We perform RL on the extended state which includes the locations and clock valuations of the timed automata for the source task. We then establish mappings between the corresponding components (clocks, locations, etc.) of the timed automata from the two tasks, and transfer the extended Q-functions based on the established mappings. Finally, we perform RL on the extended state for the target task, starting with the transferred extended Q-functions. Our results in two case studies show, depending on how similar the source task and the target task are, that the sampling efficiency for the target task can be improved by up to one order of magnitude by performing RL in the extended state space, and further improved by up to another order of magnitude using the transferred extended Q-functions.
Tasks	Transfer Learning
Published	2019-09-10
URL	https://arxiv.org/abs/1909.04256v1
PDF	https://arxiv.org/pdf/1909.04256v1.pdf
PWC	https://paperswithcode.com/paper/transfer-of-temporal-logic-formulas-in
Repo
Framework

Towards High-fidelity Nonlinear 3D Face Morphable Model


Title	Towards High-fidelity Nonlinear 3D Face Morphable Model
Authors	Luan Tran, Feng Liu, Xiaoming Liu
Abstract	Embedding 3D morphable basis functions into deep neural networks opens great potential for models with better representation power. However, to faithfully learn those models from an image collection, it requires strong regularization to overcome ambiguities involved in the learning process. This critically prevents us from learning high fidelity face models which are needed to represent face images in high level of details. To address this problem, this paper presents a novel approach to learn additional proxies as means to side-step strong regularizations, as well as, leverages to promote detailed shape/albedo. To ease the learning, we also propose to use a dual-pathway network, a carefully-designed architecture that brings a balance between global and local-based models. By improving the nonlinear 3D morphable model in both learning objective and network architecture, we present a model which is superior in capturing higher level of details than the linear or its precedent nonlinear counterparts. As a result, our model achieves state-of-the-art performance on 3D face reconstruction by solely optimizing latent representations.
Tasks	3D Face Reconstruction, Face Reconstruction
Published	2019-04-09
URL	http://arxiv.org/abs/1904.04933v1
PDF	http://arxiv.org/pdf/1904.04933v1.pdf
PWC	https://paperswithcode.com/paper/towards-high-fidelity-nonlinear-3d-face
Repo
Framework

Hierarchical Bayesian myocardial perfusion quantification


Title	Hierarchical Bayesian myocardial perfusion quantification
Authors	Cian M. Scannell, Amedeo Chiribiri, Adriana D. M. Villa, Marcel Breeuwer, Jack Lee
Abstract	Purpose: Tracer-kinetic models can be used for the quantitative assessment of contrast-enhanced MRI data. However, the model-fitting can produce unreliable results due to the limited data acquired and the high noise levels. Such problems are especially prevalent in myocardial perfusion MRI leading to the compromise of constrained numerical deconvolutions and segmental signal averaging being commonly used as alternatives to the more complex tracer-kinetic models. Methods: In this work, the use of hierarchical Bayesian inference for the parameter estimation is explored. It is shown that with Bayesian inference it is possible to reliably fit the two-compartment exchange model to perfusion data. The use of prior knowledge on the ranges of kinetic parameters and the fact that neighbouring voxels are likely to have similar kinetic properties combined with a Markov chain Monte Carlo based fitting procedure significantly improves the reliability of the perfusion estimates with compared to the traditional least-squares approach. The method is assessed using both simulated and patient data. Results: The average (standard deviation) normalised mean square error for the distinct noise realisations of a simulation phantom falls from 0.32 (0.55) with the least-squares fitting to 0.13 (0.2) using Bayesian inference. The assessment of the presence of coronary artery disease based purely on the quantitative MBF maps obtained using Bayesian inference matches the visual assessment in all 24 slices. When using the maps obtained by the least-squares fitting, a corresponding assessment is only achieved in 16/24 slices. Conclusion: Bayesian inference allows a reliable, fully automated and user-independent assessment of myocardial perfusion on a voxel-wise level using the two-compartment exchange model.
Tasks	Bayesian Inference
Published	2019-06-06
URL	https://arxiv.org/abs/1906.02540v2
PDF	https://arxiv.org/pdf/1906.02540v2.pdf
PWC	https://paperswithcode.com/paper/hierarchical-bayesian-myocardial-perfusion
Repo
Framework

Research and application of time series algorithms in centralized purchasing data


Title	Research and application of time series algorithms in centralized purchasing data
Authors	Yun Bai, Suling Jia, Xixi Li
Abstract	Based on the online transaction data of COSCO group’s centralized procurement platform, this paper studies the clustering method of time series type data. The different methods of similarity calculation, different clustering methods with different K values are analysed, and the best clustering method suitable for centralized purchasing data is determined. The company list under the corresponding cluster is obtained. The time series motif discovery algorithm is used to model the centroid of each cluster. Through ARIMA method, we also made 12 periods of prediction for the centroid of each category. This paper constructs a matrix of “Customer Lifecycle Theory - Five Elements of Marketing “, and puts forward corresponding marketing suggestions for customers at different life cycle stages.
Tasks	Time Series
Published	2019-11-01
URL	https://arxiv.org/abs/1911.00449v1
PDF	https://arxiv.org/pdf/1911.00449v1.pdf
PWC	https://paperswithcode.com/paper/research-and-application-of-time-series
Repo
Framework

FaceShifter: Towards High Fidelity And Occlusion Aware Face Swapping


Title	FaceShifter: Towards High Fidelity And Occlusion Aware Face Swapping
Authors	Lingzhi Li, Jianmin Bao, Hao Yang, Dong Chen, Fang Wen
Abstract	In this work, we propose a novel two-stage framework, called FaceShifter, for high fidelity and occlusion aware face swapping. Unlike many existing face swapping works that leverage only limited information from the target image when synthesizing the swapped face, our framework, in its first stage, generates the swapped face in high-fidelity by exploiting and integrating the target attributes thoroughly and adaptively. We propose a novel attributes encoder for extracting multi-level target face attributes, and a new generator with carefully designed Adaptive Attentional Denormalization (AAD) layers to adaptively integrate the identity and the attributes for face synthesis. To address the challenging facial occlusions, we append a second stage consisting of a novel Heuristic Error Acknowledging Refinement Network (HEAR-Net). It is trained to recover anomaly regions in a self-supervised way without any manual annotations. Extensive experiments on wild faces demonstrate that our face swapping results are not only considerably more perceptually appealing, but also better identity preserving in comparison to other state-of-the-art methods.
Tasks	Face Generation, Face Swapping
Published	2019-12-31
URL	https://arxiv.org/abs/1912.13457v1
PDF	https://arxiv.org/pdf/1912.13457v1.pdf
PWC	https://paperswithcode.com/paper/faceshifter-towards-high-fidelity-and
Repo
Framework

US-net for robust and efficient nuclei instance segmentation


Title	US-net for robust and efficient nuclei instance segmentation
Authors	Zhaoyang Xu, Faranak Sobhani, Carlos Fernandez Moro, Qianni Zhang
Abstract	We present a novel neural network architecture, US-Net, for robust nuclei instance segmentation in histopathology images. The proposed framework integrates the nuclei detection and segmentation networks by sharing their outputs through the same foundation network, and thus enhancing the performance of both. The detection network takes into account the high-level semantic cues with contextual information, while the segmentation network focuses more on the low-level details like the edges. Extensive experiments reveal that our proposed framework can strengthen the performance of both branch networks in an integrated architecture and outperforms most of the state-of-the-art nuclei detection and segmentation networks.
Tasks	Instance Segmentation, Semantic Segmentation
Published	2019-01-31
URL	http://arxiv.org/abs/1902.00125v1
PDF	http://arxiv.org/pdf/1902.00125v1.pdf
PWC	https://paperswithcode.com/paper/us-net-for-robust-and-efficient-nuclei
Repo
Framework

Detecting Deepfake-Forged Contents with Separable Convolutional Neural Network and Image Segmentation


Title	Detecting Deepfake-Forged Contents with Separable Convolutional Neural Network and Image Segmentation
Authors	Chia-Mu Yu, Ching-Tang Chang, Yen-Wu Ti
Abstract	Recent advances in AI technology have made the forgery of digital images and videos easier, and it has become significantly more difficult to identify such forgeries. These forgeries, if disseminated with malicious intent, can negatively impact social and political stability, and pose significant ethical and legal challenges as well. Deepfake is a variant of auto-encoders that use deep learning techniques to identify and exchange images of a person’s face in a picture or film. Deepfake can result in an erosion of public trust in digital images and videos, which has far-reaching effects on political and social stability. This study therefore proposes a solution for facial forgery detection to determine if a picture or film has ever been processed by Deepfake. The proposed solution reaches detection efficiency by using the recently proposed separable convolutional neural network (CNN) and image segmentation. In addition, this study also examined how different image segmentation methods affect detection results. Finally, the ensemble model is used to improve detection capabilities. Experiment results demonstrated the excellent performance of the proposed solution.
Tasks	Face Swapping, Semantic Segmentation
Published	2019-12-21
URL	https://arxiv.org/abs/1912.12184v1
PDF	https://arxiv.org/pdf/1912.12184v1.pdf
PWC	https://paperswithcode.com/paper/detecting-deepfake-forged-contents-with
Repo
Framework

FedHealth: A Federated Transfer Learning Framework for Wearable Healthcare


Title	FedHealth: A Federated Transfer Learning Framework for Wearable Healthcare
Authors	Yiqiang Chen, Jindong Wang, Chaohui Yu, Wen Gao, Xin Qin
Abstract	With the rapid development of computing technology, wearable devices such as smart phones and wristbands make it easy to get access to people’s health information including activities, sleep, sports, etc. Smart healthcare achieves great success by training machine learning models on a large quantity of user data. However, there are two critical challenges. Firstly, user data often exists in the form of isolated islands, making it difficult to perform aggregation without compromising privacy security. Secondly, the models trained on the cloud fail on personalization. In this paper, we propose FedHealth, the first federated transfer learning framework for wearable healthcare to tackle these challenges. FedHealth performs data aggregation through federated learning, and then builds personalized models by transfer learning. It is able to achieve accurate and personalized healthcare without compromising privacy and security. Experiments demonstrate that FedHealth produces higher accuracy (5.3% improvement) for wearable activity recognition when compared to traditional methods. FedHealth is general and extensible and has the potential to be used in many healthcare applications.
Tasks	Activity Recognition, Transfer Learning
Published	2019-07-22
URL	https://arxiv.org/abs/1907.09173v1
PDF	https://arxiv.org/pdf/1907.09173v1.pdf
PWC	https://paperswithcode.com/paper/fedhealth-a-federated-transfer-learning
Repo
Framework

Comparison of Deep Neural Networks and Deep Hierarchical Models for Spatio-Temporal Data


Title	Comparison of Deep Neural Networks and Deep Hierarchical Models for Spatio-Temporal Data
Authors	Christopher K. Wikle
Abstract	Spatio-temporal data are ubiquitous in the agricultural, ecological, and environmental sciences, and their study is important for understanding and predicting a wide variety of processes. One of the difficulties with modeling spatial processes that change in time is the complexity of the dependence structures that must describe how such a process varies, and the presence of high-dimensional complex data sets and large prediction domains. It is particularly challenging to specify parameterizations for nonlinear dynamic spatio-temporal models (DSTMs) that are simultaneously useful scientifically and efficient computationally. Statisticians have developed deep hierarchical models that can accommodate process complexity as well as the uncertainties in the predictions and inference. However, these models can be expensive and are typically application specific. On the other hand, the machine learning community has developed alternative “deep learning” approaches for nonlinear spatio-temporal modeling. These models are flexible yet are typically not implemented in a probabilistic framework. The two paradigms have many things in common and suggest hybrid approaches that can benefit from elements of each framework. This overview paper presents a brief introduction to the deep hierarchical DSTM (DH-DSTM) framework, and deep models in machine learning, culminating with the deep neural DSTM (DN-DSTM). Recent approaches that combine elements from DH-DSTMs and echo state network DN-DSTMs are presented as illustrations.
Tasks
Published	2019-02-22
URL	http://arxiv.org/abs/1902.08321v1
PDF	http://arxiv.org/pdf/1902.08321v1.pdf
PWC	https://paperswithcode.com/paper/comparison-of-deep-neural-networks-and-deep
Repo
Framework

Canonical Correlation Analysis (CCA) Based Multi-View Learning: An Overview


Title	Canonical Correlation Analysis (CCA) Based Multi-View Learning: An Overview
Authors	Chenfeng Guo, Dongrui Wu
Abstract	Multi-view learning (MVL) is a strategy for fusing data from different sources or subsets. Canonical correlation analysis (CCA) is very important in MVL, whose main idea is to map data from different views onto a common space with the maximum correlation. The traditional CCA can only be used to calculate the linear correlation between two views. Moreover, it is unsupervised, and the label information is wasted in supervised learning tasks. Many nonlinear, supervised, or generalized extensions have been proposed to overcome these limitations. However, to our knowledge, there is no up-to-date overview of these approaches. This paper fills this gap, by providing a comprehensive overview of many classical and latest CCA approaches, and describing their typical applications in pattern recognition, multi-modal retrieval and classification, and multi-view embedding.
Tasks	MULTI-VIEW LEARNING
Published	2019-07-03
URL	https://arxiv.org/abs/1907.01693v1
PDF	https://arxiv.org/pdf/1907.01693v1.pdf
PWC	https://paperswithcode.com/paper/canonical-correlation-analysis-cca-based
Repo
Framework

Unlimited Budget Analysis of Randomised Search Heuristics


Title	Unlimited Budget Analysis of Randomised Search Heuristics
Authors	Jun He, Thomas Jansen, Christine Zarges
Abstract	Performance analysis of all kinds of randomised search heuristics is a rapidly growing and developing field. Run time and solution quality are two popular measures of the performance of these algorithms. The focus of this paper is on the solution quality an optimisation heuristic achieves, not on the time it takes to reach this goal, setting it far apart from runtime analysis. We contribute to its further development by introducing a novel analytical framework, called unlimited budget analysis, to derive the expected fitness value after arbitrary computational steps. It has its roots in the very recently introduced approximation error analysis and bears some similarity to fixed budget analysis. We present the framework, apply it to simple mutation-based algorithms, covering both, local and global search. We provide analytical results for a number of pseudo-Boolean functions for unlimited budget analysis and compare them to results derived within the fixed budget framework for the same algorithms and functions. There are also results of experiments to compare bounds obtained in the two different frameworks with the actual observed performance. The study show that unlimited budget analysis may lead to the same or more general estimation beyond fixed budget.
Tasks
Published	2019-09-07
URL	https://arxiv.org/abs/1909.03342v2
PDF	https://arxiv.org/pdf/1909.03342v2.pdf
PWC	https://paperswithcode.com/paper/unlimited-budget-analysis-of-randomised
Repo
Framework

Passage Ranking with Weak Supervision


Title	Passage Ranking with Weak Supervision
Authors	Peng Xu, Xiaofei Ma, Ramesh Nallapati, Bing Xiang
Abstract	In this paper, we propose a \textit{weak supervision} framework for neural ranking tasks based on the data programming paradigm \citep{Ratner2016}, which enables us to leverage multiple weak supervision signals from different sources. Empirically, we consider two sources of weak supervision signals, unsupervised ranking functions and semantic feature similarities. We train a BERT-based passage-ranking model (which achieves new state-of-the-art performances on two benchmark datasets with full supervision) in our weak supervision framework. Without using ground-truth training labels, BERT-PR models outperform BM25 baseline by a large margin on all three datasets and even beat the previous state-of-the-art results with full supervision on two of the datasets.
Tasks
Published	2019-05-15
URL	https://arxiv.org/abs/1905.05910v2
PDF	https://arxiv.org/pdf/1905.05910v2.pdf
PWC	https://paperswithcode.com/paper/passage-ranking-with-weak-supervsion
Repo
Framework

Graph Neural Networks with convolutional ARMA filters


Title	Graph Neural Networks with convolutional ARMA filters
Authors	Filippo Maria Bianchi, Daniele Grattarola, Cesare Alippi, Lorenzo Livi
Abstract	Popular graph neural networks implement convolution operations on graphs based on polynomial filters defined in the spectral domain. In this paper, we propose a novel graph convolutional layer inspired by the auto-regressive moving average (ARMA) filters that, compared to the polynomial ones, are more robust and provide a more flexible graph frequency response. We propose a neural network implementation of the ARMA filter with a recursive and distributed formulation, obtaining a convolutional layer that is efficient to train, localized in the node space, and can be transferred to new graphs unseen during training. We report a spectral analysis of the proposed trainable filter, as well as experiments on four major downstream tasks: semi-supervised node classification, graph signal classification, graph classification, and graph regression. The results show that ARMA filters bring significant improvements over graph neural networks based on polynomial filters.
Tasks	Graph Classification, Graph Regression, Node Classification, Skeleton Based Action Recognition
Published	2019-01-05
URL	https://arxiv.org/abs/1901.01343v5
PDF	https://arxiv.org/pdf/1901.01343v5.pdf
PWC	https://paperswithcode.com/paper/graph-neural-networks-with-convolutional-arma
Repo
Framework