January 26, 2020

3027 words 15 mins read

Paper Group ANR 1470

Fully Bayesian Recurrent Neural Networks for Safe Reinforcement Learning. Deep Learning for Estimating Synaptic Health of Primary Neuronal Cell Culture. Imitating Targets from all sides: An Unsupervised Transfer Learning method for Person Re-identification. Bayesian Learning of Sum-Product Networks. Heuristic Dynamic Programming for Adaptive Virtua …

Fully Bayesian Recurrent Neural Networks for Safe Reinforcement Learning


Title	Fully Bayesian Recurrent Neural Networks for Safe Reinforcement Learning
Authors	Matt Benatan, Edward O. Pyzer-Knapp
Abstract	Reinforcement Learning (RL) has demonstrated state-of-the-art results in a number of autonomous system applications, however many of the underlying algorithms rely on black-box predictions. This results in poor explainability of the behaviour of these systems, raising concerns as to their use in safety-critical applications. Recent work has demonstrated that uncertainty-aware models exhibit more cautious behaviours through the incorporation of model uncertainty estimates. In this work, we build on Probabilistic Backpropagation to introduce a fully Bayesian Recurrent Neural Network architecture. We apply this within a Safe RL scenario, and demonstrate that the proposed method significantly outperforms a popular approach for obtaining model uncertainties in collision avoidance tasks. Furthermore, we demonstrate that the proposed approach requires less training and is far more efficient than the current leading method, both in terms of compute resource and memory footprint.
Tasks
Published	2019-11-08
URL	https://arxiv.org/abs/1911.03308v2
PDF	https://arxiv.org/pdf/1911.03308v2.pdf
PWC	https://paperswithcode.com/paper/fully-bayesian-recurrent-neural-networks-for
Repo
Framework

Deep Learning for Estimating Synaptic Health of Primary Neuronal Cell Culture


Title	Deep Learning for Estimating Synaptic Health of Primary Neuronal Cell Culture
Authors	Andrey Kormilitzin, Xinyu Yang, William H. Stone, Caroline Woffindale, Francesca Nicholls, Elena Ribe, Alejo Nevado-Holgado, Noel Buckley
Abstract	Understanding the morphological changes of primary neuronal cells induced by chemical compounds is essential for drug discovery. Using the data from a single high-throughput imaging assay, a classification model for predicting the biological activity of candidate compounds was introduced. The image recognition model which is based on deep convolutional neural network (CNN) architecture with residual connections achieved accuracy of 99.6$%$ on a binary classification task of distinguishing untreated and treated rodent primary neuronal cells with Amyloid-$\beta_{(25-35)}$.
Tasks	Drug Discovery
Published	2019-08-29
URL	https://arxiv.org/abs/1908.11399v1
PDF	https://arxiv.org/pdf/1908.11399v1.pdf
PWC	https://paperswithcode.com/paper/deep-learning-for-estimating-synaptic-health
Repo
Framework

Imitating Targets from all sides: An Unsupervised Transfer Learning method for Person Re-identification


Title	Imitating Targets from all sides: An Unsupervised Transfer Learning method for Person Re-identification
Authors	Jiajie Tian, Zhu Teng, Rui Li, Yan Li, Baopeng Zhang, Jianping Fan
Abstract	Person re-identification (Re-ID) models usually show a limited performance when they are trained on one dataset and tested on another dataset due to the inter-dataset bias (e.g. completely different identities and backgrounds) and the intra-dataset difference (e.g. camera invariance). In terms of this issue, given a labelled source training set and an unlabelled target training set, we propose an unsupervised transfer learning method characterized by 1) bridging inter-dataset bias and intra-dataset difference via a proposed ImitateModel simultaneously; 2) regarding the unsupervised person Re-ID problem as a semi-supervised learning problem formulated by a dual classification loss to learn a discriminative representation across domains; 3) exploiting the underlying commonality across different domains from the class-style space to improve the generalization ability of re-ID models. Extensive experiments are conducted on two widely employed benchmarks, including Market-1501 and DukeMTMC-reID, and experimental results demonstrate that the proposed method can achieve a competitive performance against other state-of-the-art unsupervised Re-ID approaches.
Tasks	Person Re-Identification, Transfer Learning
Published	2019-04-10
URL	http://arxiv.org/abs/1904.05020v1
PDF	http://arxiv.org/pdf/1904.05020v1.pdf
PWC	https://paperswithcode.com/paper/imitating-targets-from-all-sides-an
Repo
Framework

Bayesian Learning of Sum-Product Networks


Title	Bayesian Learning of Sum-Product Networks
Authors	Martin Trapp, Robert Peharz, Hong Ge, Franz Pernkopf, Zoubin Ghahramani
Abstract	Sum-product networks (SPNs) are flexible density estimators and have received significant attention due to their attractive inference properties. While parameter learning in SPNs is well developed, structure learning leaves something to be desired: Even though there is a plethora of SPN structure learners, most of them are somewhat ad-hoc and based on intuition rather than a clear learning principle. In this paper, we introduce a well-principled Bayesian framework for SPN structure learning. First, we decompose the problem into i) laying out a computational graph, and ii) learning the so-called scope function over the graph. The first is rather unproblematic and akin to neural network architecture validation. The second represents the effective structure of the SPN and needs to respect the usual structural constraints in SPN, i.e. completeness and decomposability. While representing and learning the scope function is somewhat involved in general, in this paper, we propose a natural parametrisation for an important and widely used special case of SPNs. These structural parameters are incorporated into a Bayesian model, such that simultaneous structure and parameter learning is cast into monolithic Bayesian posterior inference. In various experiments, our Bayesian SPNs often improve test likelihoods over greedy SPN learners. Further, since the Bayesian framework protects against overfitting, we can evaluate hyper-parameters directly on the Bayesian model score, waiving the need for a separate validation set, which is especially beneficial in low data regimes. Bayesian SPNs can be applied to heterogeneous domains and can easily be extended to nonparametric formulations. Moreover, our Bayesian approach is the first, which consistently and robustly learns SPN structures under missing data.
Tasks
Published	2019-05-26
URL	https://arxiv.org/abs/1905.10884v3
PDF	https://arxiv.org/pdf/1905.10884v3.pdf
PWC	https://paperswithcode.com/paper/bayesian-learning-of-sum-product-networks
Repo
Framework

Heuristic Dynamic Programming for Adaptive Virtual Synchronous Generators


Title	Heuristic Dynamic Programming for Adaptive Virtual Synchronous Generators
Authors	Sepehr Saadatmand, Mohammad Saleh Sanjarinia, Pourya Shamsi, Mehdi Ferdowsi, Donald C. Wunsch
Abstract	In this paper a neural network heuristic dynamic programing (HDP) is used for optimal control of the virtual inertia based control of grid connected three phase inverters. It is shown that the conventional virtual inertia controllers are not suited for non inductive grids. A neural network based controller is proposed to adapt to any impedance angle. Applying an adaptive dynamic programming controller instead of a supervised controlled method enables the system to adjust itself to different conditions. The proposed HDP consists of two subnetworks, critic network and action network. These networks can be trained during the same training cycle to decrease the training time. The simulation results confirm that the proposed neural network HDP controller performs better than the traditional direct fed voltage and reactive power controllers in virtual inertia control schemes.
Tasks
Published	2019-08-14
URL	https://arxiv.org/abs/1908.05744v1
PDF	https://arxiv.org/pdf/1908.05744v1.pdf
PWC	https://paperswithcode.com/paper/heuristic-dynamic-programming-for-adaptive
Repo
Framework

Data-based wind disaster climate identification algorithm and extreme wind speed prediction


Title	Data-based wind disaster climate identification algorithm and extreme wind speed prediction
Authors	Wei Cui, Teng Ma, Lin Zhao, Yaojun Ge
Abstract	An extreme wind speed estimation method that considers wind hazard climate types is critical for design wind load calculation for building structures affected by mixed climates. However, it is very difficult to obtain wind hazard climate types from meteorological data records, because they restrict the application of extreme wind speed estimation in mixed climates. This paper first proposes a wind hazard type identification algorithm based on a numerical pattern recognition method that utilizes feature extraction and generalization. Next, it compares six commonly used machine learning models using K-fold cross-validation. Finally, it takes meteorological data from three locations near the southeast coast of China as examples to examine the algorithm performance. Based on classification results, the extreme wind speeds calculated based on mixed wind hazard types is compared with those obtained from conventional methods, and the effects on structural design for different return periods are discussed.
Tasks
Published	2019-08-29
URL	https://arxiv.org/abs/1908.11051v1
PDF	https://arxiv.org/pdf/1908.11051v1.pdf
PWC	https://paperswithcode.com/paper/data-based-wind-disaster-climate
Repo
Framework

On Detecting GANs and Retouching based Synthetic Alterations


Title	On Detecting GANs and Retouching based Synthetic Alterations
Authors	Anubhav Jain, Richa Singh, Mayank Vatsa
Abstract	Digitally retouching images has become a popular trend, with people posting altered images on social media and even magazines posting flawless facial images of celebrities. Further, with advancements in Generative Adversarial Networks (GANs), now changing attributes and retouching have become very easy. Such synthetic alterations have adverse effect on face recognition algorithms. While researchers have proposed to detect image tampering, detecting GANs generated images has still not been explored. This paper proposes a supervised deep learning algorithm using Convolutional Neural Networks (CNNs) to detect synthetically altered images. The algorithm yields an accuracy of 99.65% on detecting retouching on the ND-IIITD dataset. It outperforms the previous state of the art which reported an accuracy of 87% on the database. For distinguishing between real images and images generated using GANs, the proposed algorithm yields an accuracy of 99.83%.
Tasks	Face Recognition
Published	2019-01-26
URL	http://arxiv.org/abs/1901.09237v1
PDF	http://arxiv.org/pdf/1901.09237v1.pdf
PWC	https://paperswithcode.com/paper/on-detecting-gans-and-retouching-based
Repo
Framework

Learning Schatten–von Neumann Operators


Title	Learning Schatten–von Neumann Operators
Authors	Puoya Tabaghi, Maarten de Hoop, Ivan Dokmanić
Abstract	We study the learnability of a class of compact operators known as Schatten–von Neumann operators. These operators between infinite-dimensional function spaces play a central role in a variety of applications in learning theory and inverse problems. We address the question of sample complexity of learning Schatten-von Neumann operators and provide an upper bound on the number of measurements required for the empirical risk minimizer to generalize with arbitrary precision and probability, as a function of class parameter $p$. Our results give generalization guarantees for regression of infinite-dimensional signals from infinite-dimensional data. Next, we adapt the representer theorem of Abernethy \emph{et al.} to show that empirical risk minimization over an a priori infinite-dimensional, non-compact set, can be converted to a convex finite dimensional optimization problem over a compact set. In summary, the class of $p$-Schatten–von Neumann operators is probably approximately correct (PAC)-learnable via a practical convex program for any $p < \infty$.
Tasks
Published	2019-01-29
URL	http://arxiv.org/abs/1901.10076v2
PDF	http://arxiv.org/pdf/1901.10076v2.pdf
PWC	https://paperswithcode.com/paper/learning-schatten-von-neumann-operators
Repo
Framework

Change Detection and Notification of Webpages: A Survey


Title	Change Detection and Notification of Webpages: A Survey
Authors	Vijini Mallawaarachchi, Lakmal Meegahapola, Roshan Alwis, Eranga Nimalarathna, Dulani Meedeniya, Sampath Jayarathna
Abstract	Majority of the currently available webpages are dynamic in nature and are changing frequently. New content gets added to webpages and existing content gets updated or deleted. Hence, people find it useful to be alert for changes in webpages which contain information valuable to them. In the current context, keeping track of these webpages and getting alerts about different changes have become significantly challenging. Change Detection and Notification (CDN) systems were introduced to automate this monitoring process and notify users when changes occur in webpages. This survey classifies and analyzes different aspects of CDN systems and different techniques used for each aspect. Furthermore, the survey highlights the current challenges and areas of improvement present within the field of research.
Tasks
Published	2019-01-09
URL	https://arxiv.org/abs/1901.02660v4
PDF	https://arxiv.org/pdf/1901.02660v4.pdf
PWC	https://paperswithcode.com/paper/change-detection-and-notification-of-webpages
Repo
Framework

Lion Algorithm- Optimized Long Short-Term Memory Network for Groundwater Level Forecasting in Udupi District, India


Title	Lion Algorithm- Optimized Long Short-Term Memory Network for Groundwater Level Forecasting in Udupi District, India
Authors	Supreetha B. S, Narayan Shenoy, Prabhakar Nayak
Abstract	Groundwater is a precious natural resource. Groundwater level (GWL) forecasting is crucial in the field of water resource management. Measurement of GWL from observation-wells is the principle source of information about the aquifer and is critical to its evaluation. Most part of the Udupi district of Karnataka State in India consists of geological formations: lateritic terrain and gneissic complex. Due to the topographical ruggedness and inconsistency in rainfall, the GWL in Udupi region is declining continually and most of the open wells are drying-up during the summer. Hence, the current research aimed at developing a groundwater level forecasting model by using hybrid Long Short-term Memory-Lion Algorithm (LSTM-LA). The historical GWL and rainfall data from an observation well from Udupi district, located in Karnataka state, India, were used to develop the model. The prediction accuracy of the hybrid LSTM-LA model was better than that of the Feedforward Neural network (FFNN) and the isolated LSTM models. The hybrid LSTM-LA based forecasting model is promising for a larger dataset.
Tasks
Published	2019-12-05
URL	https://arxiv.org/abs/1912.05934v1
PDF	https://arxiv.org/pdf/1912.05934v1.pdf
PWC	https://paperswithcode.com/paper/lion-algorithm-optimized-long-short-term
Repo
Framework

A Novel Unsupervised Camera-aware Domain Adaptation Framework for Person Re-identification


Title	A Novel Unsupervised Camera-aware Domain Adaptation Framework for Person Re-identification
Authors	Lei Qi, Lei Wang, Jing Huo, Luping Zhou, Yinghuan Shi, Yang Gao
Abstract	Unsupervised cross-domain person re-identification (Re-ID) faces two key issues. One is the data distribution discrepancy between source and target domains, and the other is the lack of labelling information in target domain. They are addressed in this paper from the perspective of representation learning. For the first issue, we highlight the presence of camera-level sub-domains as a unique characteristic of person Re-ID, and develop camera-aware domain adaptation to reduce the discrepancy not only between source and target domains but also across these sub-domains. For the second issue, we exploit the temporal continuity in each camera of target domain to create discriminative information. This is implemented by dynamically generating online triplets within each batch, in order to maximally take advantage of the steadily improved feature representation in training process. Together, the above two methods give rise to a novel unsupervised deep domain adaptation framework for person Re-ID. Experiments and ablation studies on benchmark datasets demonstrate its superiority and interesting properties.
Tasks	Domain Adaptation, Person Re-Identification, Representation Learning
Published	2019-04-06
URL	https://arxiv.org/abs/1904.03425v2
PDF	https://arxiv.org/pdf/1904.03425v2.pdf
PWC	https://paperswithcode.com/paper/a-novel-unsupervised-camera-aware-domain
Repo
Framework

Multi-stream CNN based Video Semantic Segmentation for Automated Driving


Title	Multi-stream CNN based Video Semantic Segmentation for Automated Driving
Authors	Ganesh Sistu, Sumanth Chennupati, Senthil Yogamani
Abstract	Majority of semantic segmentation algorithms operate on a single frame even in the case of videos. In this work, the goal is to exploit temporal information within the algorithm model for leveraging motion cues and temporal consistency. We propose two simple high-level architectures based on Recurrent FCN (RFCN) and Multi-Stream FCN (MSFCN) networks. In case of RFCN, a recurrent network namely LSTM is inserted between the encoder and decoder. MSFCN combines the encoders of different frames into a fused encoder via 1x1 channel-wise convolution. We use a ResNet50 network as the baseline encoder and construct three networks namely MSFCN of order 2 & 3 and RFCN of order 2. MSFCN-3 produces the best results with an accuracy improvement of 9% and 15% for Highway and New York-like city scenarios in the SYNTHIA-CVPR’16 dataset using mean IoU metric. MSFCN-3 also produced 11% and 6% for SegTrack V2 and DAVIS datasets over the baseline FCN network. We also designed an efficient version of MSFCN-2 and RFCN-2 using weight sharing among the two encoders. The efficient MSFCN-2 provided an improvement of 11% and 5% for KITTI and SYNTHIA with negligible increase in computational complexity compared to the baseline version.
Tasks	Semantic Segmentation, Video Semantic Segmentation
Published	2019-01-08
URL	http://arxiv.org/abs/1901.02511v1
PDF	http://arxiv.org/pdf/1901.02511v1.pdf
PWC	https://paperswithcode.com/paper/multi-stream-cnn-based-video-semantic
Repo
Framework

Unsupervised Visual Representation Learning with Increasing Object Shape Bias


Title	Unsupervised Visual Representation Learning with Increasing Object Shape Bias
Authors	Zhibo Wang, Shen Yan, Xiaoyu Zhang, Niels Lobo
Abstract	(Very early draft)Traditional supervised learning keeps pushing convolution neural network(CNN) achieving state-of-art performance. However, lack of large-scale annotation data is always a big problem due to the high cost of it, even ImageNet dataset is over-fitted by complex models now. The success of unsupervised learning method represented by the Bert model in natural language processing(NLP) field shows its great potential. And it makes that unlimited training samples becomes possible and the great universal generalization ability changes NLP research direction directly. In this article, we purpose a novel unsupervised learning method based on contrastive predictive coding. Under that, we are able to train model with any non-annotation images and improve model’s performance to reach state-of-art performance at the same level of model complexity. Beside that, since the number of training images could be unlimited amplification, an universal large-scale pre-trained computer vision model is possible in the future.
Tasks	Representation Learning
Published	2019-11-17
URL	https://arxiv.org/abs/1911.07272v2
PDF	https://arxiv.org/pdf/1911.07272v2.pdf
PWC	https://paperswithcode.com/paper/unsupervised-visual-representation-learning-2
Repo
Framework

Robust Importance Weighting for Covariate Shift


Title	Robust Importance Weighting for Covariate Shift
Authors	Henry Lam, Fengpei Li, Siddharth Prusty
Abstract	In many learning problems, the training and testing data follow different distributions and a particularly common situation is the \textit{covariate shift}. To correct for sampling biases, most approaches, including the popular kernel mean matching (KMM), focus on estimating the importance weights between the two distributions. Reweighting-based methods, however, are exposed to high variance when the distributional discrepancy is large and the weights are poorly estimated. On the other hand, the alternate approach of using nonparametric regression (NR) incurs high bias when the training size is limited. In this paper, we propose and analyze a new estimator that systematically integrates the residuals of NR with KMM reweighting, based on a control-variate perspective. The proposed estimator can be shown to either strictly outperform or match the best-known existing rates for both KMM and NR, and thus is a robust combination of both estimators. The experiments shows the estimator works well in practice.
Tasks
Published	2019-10-14
URL	https://arxiv.org/abs/1910.06324v2
PDF	https://arxiv.org/pdf/1910.06324v2.pdf
PWC	https://paperswithcode.com/paper/robust-importance-weighting-for-covariate
Repo
Framework

Preference-Based Batch and Sequential Teaching: Towards a Unified View of Models


Title	Preference-Based Batch and Sequential Teaching: Towards a Unified View of Models
Authors	Farnam Mansouri, Yuxin Chen, Ara Vartanian, Xiaojin Zhu, Adish Singla
Abstract	Algorithmic machine teaching studies the interaction between a teacher and a learner where the teacher selects labeled examples aiming at teaching a target hypothesis. In a quest to lower teaching complexity and to achieve more natural teacher-learner interactions, several teaching models and complexity measures have been proposed for both the batch settings (e.g., worst-case, recursive, preference-based, and non-clashing models) as well as the sequential settings (e.g., local preference-based model). To better understand the connections between these different batch and sequential models, we develop a novel framework which captures the teaching process via preference functions $\Sigma$. In our framework, each function $\sigma \in \Sigma$ induces a teacher-learner pair with teaching complexity as $\TD(\sigma)$. We show that the above-mentioned teaching models are equivalent to specific types/families of preference functions in our framework. This equivalence, in turn, allows us to study the differences between two important teaching models, namely $\sigma$ functions inducing the strongest batch (i.e., non-clashing) model and $\sigma$ functions inducing a weak sequential (i.e., local preference-based) model. Finally, we identify preference functions inducing a novel family of sequential models with teaching complexity linear in the VC dimension of the hypothesis class: this is in contrast to the best known complexity result for the batch models which is quadratic in the VC dimension.
Tasks
Published	2019-10-24
URL	https://arxiv.org/abs/1910.10944v1
PDF	https://arxiv.org/pdf/1910.10944v1.pdf
PWC	https://paperswithcode.com/paper/preference-based-batch-and-sequential
Repo
Framework