January 27, 2020

3164 words 15 mins read

Paper Group ANR 1117

Cross Domain Image Matching in Presence of Outliers. Measuring Dataset Granularity. Resolvable Designs for Speeding up Distributed Computing. Representing and Using Knowledge with the Contextual Evaluation Model. Forecasting Stock Market with Support Vector Regression and Butterfly Optimization Algorithm. Learning sparsity in reservoir computing th …

Cross Domain Image Matching in Presence of Outliers


Title	Cross Domain Image Matching in Presence of Outliers
Authors	Xin Liu, Seyran Khademi, Jan C. van Gemert
Abstract	Cross domain image matching between image collections from different source and target domains is challenging in times of deep learning due to i) limited variation of image conditions in a training set, ii) lack of paired-image labels during training, iii) the existing of outliers that makes image matching domains not fully overlap. To this end, we propose an end-to-end architecture that can match cross domain images without labels in the target domain and handle non-overlapping domains by outlier detection. We leverage domain adaptation and triplet constraints for training a network capable of learning domain invariant and identity distinguishable representations, and iteratively detecting the outliers with an entropy loss and our proposed weighted MK-MMD. Extensive experimental evidence on Office [17] dataset and our proposed datasets Shape, Pitts-CycleGAN shows that the proposed approach yields state-of-the-art cross domain image matching and outlier detection performance on different benchmarks. The code will be made publicly available.
Tasks	Domain Adaptation, Outlier Detection
Published	2019-09-08
URL	https://arxiv.org/abs/1909.03552v1
PDF	https://arxiv.org/pdf/1909.03552v1.pdf
PWC	https://paperswithcode.com/paper/cross-domain-image-matching-in-presence-of
Repo
Framework

Measuring Dataset Granularity


Title	Measuring Dataset Granularity
Authors	Yin Cui, Zeqi Gu, Dhruv Mahajan, Laurens van der Maaten, Serge Belongie, Ser-Nam Lim
Abstract	Despite the increasing visibility of fine-grained recognition in our field, “fine-grained’’ has thus far lacked a precise definition. In this work, building upon clustering theory, we pursue a framework for measuring dataset granularity. We argue that dataset granularity should depend not only on the data samples and their labels, but also on the distance function we choose. We propose an axiomatic framework to capture desired properties for a dataset granularity measure and provide examples of measures that satisfy these properties. We assess each measure via experiments on datasets with hierarchical labels of varying granularity. When measuring granularity in commonly used datasets with our measure, we find that certain datasets that are widely considered fine-grained in fact contain subsets of considerable size that are substantially more coarse-grained than datasets generally regarded as coarse-grained. We also investigate the interplay between dataset granularity with a variety of factors and find that fine-grained datasets are more difficult to learn from, more difficult to transfer to, more difficult to perform few-shot learning with, and more vulnerable to adversarial attacks.
Tasks	Few-Shot Learning
Published	2019-12-21
URL	https://arxiv.org/abs/1912.10154v1
PDF	https://arxiv.org/pdf/1912.10154v1.pdf
PWC	https://paperswithcode.com/paper/measuring-dataset-granularity
Repo
Framework

Resolvable Designs for Speeding up Distributed Computing


Title	Resolvable Designs for Speeding up Distributed Computing
Authors	Konstantinos Konstantinidis, Aditya Ramamoorthy
Abstract	Distributed computing frameworks such as MapReduce are often used to process large computational jobs. They operate by partitioning each job into smaller tasks executed on different servers. The servers also need to exchange intermediate values to complete the computation. Experimental evidence suggests that this so-called Shuffle phase can be a significant part of the overall execution time for several classes of jobs. Prior work has demonstrated a natural tradeoff between computation and communication whereby running redundant copies of jobs can reduce the Shuffle traffic load, thereby leading to reduced overall execution times. For a single job, the main drawback of this approach is that it requires the original job to be split into a number of files that grows exponentially in the system parameters. When extended to multiple jobs (with specific function types), these techniques suffer from a limitation of a similar flavor, i.e., they require an exponentially large number of jobs to be executed. In practical scenarios, these requirements can significantly reduce the promised gains of the method. In this work, we show that a class of combinatorial structures called resolvable designs can be used to develop efficient coded distributed computing schemes for both the single and multiple job scenarios considered in prior work. We present both theoretical analysis and exhaustive experimental results (on Amazon EC2 clusters) that demonstrate the performance advantages of our method. For the single and multiple job cases, we obtain speed-ups of 4.69x (and 2.6x over prior work) and 4.31x over the baseline approach, respectively.
Tasks
Published	2019-08-14
URL	https://arxiv.org/abs/1908.05666v2
PDF	https://arxiv.org/pdf/1908.05666v2.pdf
PWC	https://paperswithcode.com/paper/resolvable-designs-for-speeding-up
Repo
Framework

Representing and Using Knowledge with the Contextual Evaluation Model


Title	Representing and Using Knowledge with the Contextual Evaluation Model
Authors	Victor E Hansen
Abstract	This paper introduces the Contextual Evaluation Model (CEM), a novel method for knowledge representation and manipulation. The CEM differs from existing models in that it integrates facts, patterns and sequences into a single contextual framework. V5, an implementation of the model is presented and demonstrated with multiple annotated examples. The paper includes simulations demonstrating how the model reacts to pleasure/pain stimuli. The ‘thought’ is defined within the model and examples are given converting thoughts to language, converting language to thoughts and how ‘meaning’ arises from thoughts. A pattern learning algorithm is described. The algorithm is applied to multiple problems ranging from recognizing a voice to the autonomous learning of a simplified natural language.
Tasks
Published	2019-05-31
URL	https://arxiv.org/abs/1906.03253v1
PDF	https://arxiv.org/pdf/1906.03253v1.pdf
PWC	https://paperswithcode.com/paper/representing-and-using-knowledge-with-the
Repo
Framework

Forecasting Stock Market with Support Vector Regression and Butterfly Optimization Algorithm


Title	Forecasting Stock Market with Support Vector Regression and Butterfly Optimization Algorithm
Authors	Mohammadreza Ghanbari, Hamidreza Arian
Abstract	Support Vector Regression (SVR) has achieved high performance on forecasting future behavior of random systems. However, the performance of SVR models highly depends upon the appropriate choice of SVR parameters. In this study, a novel BOA-SVR model based on Butterfly Optimization Algorithm (BOA) is presented. The performance of the proposed model is compared with eleven other meta-heuristic algorithms on a number of stocks from NASDAQ. The results indicate that the presented model here is capable to optimize the SVR parameters very well and indeed is one of the best models judged by both prediction performance accuracy and time consumption.
Tasks
Published	2019-05-27
URL	https://arxiv.org/abs/1905.11462v1
PDF	https://arxiv.org/pdf/1905.11462v1.pdf
PWC	https://paperswithcode.com/paper/forecasting-stock-market-with-support-vector
Repo
Framework

Learning sparsity in reservoir computing through a novel bio-inspired algorithm


Title	Learning sparsity in reservoir computing through a novel bio-inspired algorithm
Authors	Luca Manneschi, Andrew C. Lin, Eleni Vasilaki
Abstract	The mushroom body is the key network for the representation of learned olfactory stimuli in Drosophila and insects. The sparse activity of Kenyon cells, the principal neurons in the mushroom body, plays a key role in the learned classification of different odours. In the specific case of the fruit fly, the sparseness of the network is enforced by an inhibitory feedback neuron called APL, and by an intrinsic high firing threshold of the Kenyon cells. In this work we took inspiration from the fruit fly brain to formulate a novel machine learning algorithm that is able to optimize the sparsity level of a reservoir by changing the firing thresholds of the nodes. The sparsity is only applied on the readout layer so as not to change the timescales of the reservoir and to allow the derivation of a one-layer update rule for the firing thresholds. The proposed algorithm is a combination of learning a neuron-specific sparsity threshold via gradient descent and a global sparsity threshold via a Markov chain Monte Carlo method. The proposed model outperforms the standard gradient descent, which is limited to the readout weights of the reservoir, on two example tasks. It demonstrates how the learnt sparse representation can lead to better classification performance, memorization ability and convergence time.
Tasks
Published	2019-07-19
URL	https://arxiv.org/abs/1907.08600v1
PDF	https://arxiv.org/pdf/1907.08600v1.pdf
PWC	https://paperswithcode.com/paper/learning-sparsity-in-reservoir-computing
Repo
Framework

Revisiting Few-Shot Learning for Facial Expression Recognition


Title	Revisiting Few-Shot Learning for Facial Expression Recognition
Authors	Anca-Nicoleta Ciubotaru, Arnout Devos, Behzad Bozorgtabar, Jean-Philippe Thiran, Maria Gabrani
Abstract	Most of the existing deep neural nets on automatic facial expression recognition focus on a set of predefined emotion classes, where the amount of training data has the biggest impact on performance. However, in the standard setting over-parameterised neural networks are not amenable for learning from few samples as they can quickly over-fit. In addition, these approaches do not have such a strong generalisation ability to identify a new category, where the data of each category is too limited and significant variations exist in the expression within the same semantic category. We embrace these challenges and formulate the problem as a low-shot learning, where once the base classifier is deployed, it must rapidly adapt to recognise novel classes using a few samples. In this paper, we revisit and compare existing few-shot learning methods for the low-shot facial expression recognition in terms of their generalisation ability via episode-training. In particular, we extend our analysis on the cross-domain generalisation, where training and test tasks are not drawn from the same distribution. We demonstrate the efficacy of low-shot learning methods through extensive experiments.
Tasks	Facial Expression Recognition, Few-Shot Learning
Published	2019-12-05
URL	https://arxiv.org/abs/1912.02751v2
PDF	https://arxiv.org/pdf/1912.02751v2.pdf
PWC	https://paperswithcode.com/paper/revisiting-few-shot-learning-for-facial
Repo
Framework

Facial Expression Representation Learning by Synthesizing Expression Images


Title	Facial Expression Representation Learning by Synthesizing Expression Images
Authors	Kamran Ali, Charles E. Hughes
Abstract	Representations used for Facial Expression Recognition (FER) usually contain expression information along with identity features. In this paper, we propose a novel Disentangled Expression learning-Generative Adversarial Network (DE-GAN) which combines the concept of disentangled representation learning with residue learning to explicitly disentangle facial expression representation from identity information. In this method the facial expression representation is learned by reconstructing an expression image employing an encoder-decoder based generator. Unlike previous works using only expression residual learning for facial expression recognition, our method learns the disentangled expression representation along with the expressive component recorded by the encoder of DE-GAN. In order to improve the quality of synthesized expression images and the effectiveness of the learned disentangled expression representation, expression and identity classification is performed by the discriminator of DE-GAN. Experiments performed on widely used datasets (CK+, MMI, Oulu-CASIA) show that the proposed technique produces comparable or better results than state-of-the-art methods.
Tasks	Facial Expression Recognition, Representation Learning
Published	2019-11-30
URL	https://arxiv.org/abs/1912.01456v1
PDF	https://arxiv.org/pdf/1912.01456v1.pdf
PWC	https://paperswithcode.com/paper/facial-expression-representation-learning-by
Repo
Framework

All-In-One: Facial Expression Transfer, Editing and Recognition Using A Single Network


Title	All-In-One: Facial Expression Transfer, Editing and Recognition Using A Single Network
Authors	Kamran Ali, Charles E. Hughes
Abstract	In this paper, we present a unified architecture known as Transfer-Editing and Recognition Generative Adversarial Network (TER-GAN) which can be used: 1. to transfer facial expressions from one identity to another identity, known as Facial Expression Transfer (FET), 2. to transform the expression of a given image to a target expression, while preserving the identity of the image, known as Facial Expression Editing (FEE), and 3. to recognize the facial expression of a face image, known as Facial Expression Recognition (FER). In TER-GAN, we combine the capabilities of generative models to generate synthetic images, while learning important information about the input images during the reconstruction process. More specifically, two encoders are used in TER-GAN to encode identity and expression information from two input images, and a synthetic expression image is generated by the decoder part of TER-GAN. To improve the feature disentanglement and extraction process, we also introduce a novel expression consistency loss and an identity consistency loss which exploit extra expression and identity information from generated images. Experimental results show that the proposed method can be used for efficient facial expression transfer, facial expression editing and facial expression recognition. In order to evaluate the proposed technique and to compare our results with state-of-the-art methods, we have used the Oulu-CASIA dataset for our experiments.
Tasks	Facial Expression Recognition
Published	2019-11-16
URL	https://arxiv.org/abs/1911.07050v1
PDF	https://arxiv.org/pdf/1911.07050v1.pdf
PWC	https://paperswithcode.com/paper/all-in-one-facial-expression-transfer-editing
Repo
Framework

Enriching Conversation Context in Retrieval-based Chatbots


Title	Enriching Conversation Context in Retrieval-based Chatbots
Authors	Amir Vakili Tahami, Azadeh Shakery
Abstract	Work on retrieval-based chatbots, like most sequence pair matching tasks, can be divided into Cross-encoders that perform word matching over the pair, and Bi-encoders that encode the pair separately. The latter has better performance, however since candidate responses cannot be encoded offline, it is also much slower. Lately, multi-layer transformer architectures pre-trained as language models have been used to great effect on a variety of natural language processing and information retrieval tasks. Recent work has shown that these language models can be used in text-matching scenarios to create Bi-encoders that perform almost as well as Cross-encoders while having a much faster inference speed. In this paper, we expand upon this work by developing a sequence matching architecture that %takes into account contexts in the training dataset at inference time. utilizes the entire training set as a makeshift knowledge-base during inference. We perform detailed experiments demonstrating that this architecture can be used to further improve Bi-encoders performance while still maintaining a relatively high inference speed.
Tasks	Information Retrieval, Text Matching
Published	2019-11-06
URL	https://arxiv.org/abs/1911.02290v1
PDF	https://arxiv.org/pdf/1911.02290v1.pdf
PWC	https://paperswithcode.com/paper/enriching-conversation-context-in-retrieval
Repo
Framework

Process of image super-resolution


Title	Process of image super-resolution
Authors	Sebastien Lablanche, Gerard Lablanche
Abstract	In this paper we explain a process of super-resolution reconstruction allowing to increase the resolution of an image.The need for high-resolution digital images exists in diverse domains, for example the medical and spatial domains. The obtaining of high-resolution digital images can be made at the time of the shooting, but it is often synonymic of important costs because of the necessary material to avoid such costs, it is known how to use methods of super-resolution reconstruction, consisting from one or several low resolution images to obtain a high-resolution image. The american patent US 9 208 537 describes such an algorithm. A zone of one low-resolution image is isolated and categorized according to the information contained in pixels forming the borders of the zone. The category of it zone determines the type of interpolation used to add pixels in aforementioned zone, to increase the neatness of the images. It is also known how to reconstruct a low-resolution image there high-resolution image by using a model of super-resolution reconstruction whose learning is based on networks of neurons and on image or a picture library. The demand of chinese patent CN 107563965 and the scientist publication “Pixel Recursive Super Resolution”, R. Dahl, M. Norouzi, J. Shlens propose such methods.
Tasks	Image Super-Resolution, Super-Resolution
Published	2019-04-17
URL	https://arxiv.org/abs/1904.08396v5
PDF	https://arxiv.org/pdf/1904.08396v5.pdf
PWC	https://paperswithcode.com/paper/process-of-image-super-resolution
Repo
Framework

Circuit-Based Intrinsic Methods to Detect Overfitting


Title	Circuit-Based Intrinsic Methods to Detect Overfitting
Authors	Sat Chatterjee, Alan Mishchenko
Abstract	The focus of this paper is on intrinsic methods to detect overfitting. These rely only on the model and the training data, as opposed to traditional extrinsic methods that rely on performance on a test set or on bounds from model complexity. We propose a family of intrinsic methods called Counterfactual Simulation (CFS) which analyze the flow of training examples through the model by identifying and perturbing rare patterns. By applying CFS to logic circuits we get a method that has no hyper-parameters and works uniformly across different types of models such as neural networks, random forests and lookup tables. Experimentally, CFS can separate models with different levels of overfit using only their logic circuit representations without any access to the high level structure. By comparing lookup tables, neural networks, and random forests using CFS, we get insight into why neural networks generalize. In particular, we find that stochastic gradient descent in neural nets does not lead to “brute force” memorization, but finds common patterns (whether we train with actual or randomized labels), and neural networks are not unlike forests in this regard. Finally, we identify a limitation with our proposal that makes it unsuitable in an adversarial setting, but points the way to future work on robust intrinsic methods.
Tasks
Published	2019-07-03
URL	https://arxiv.org/abs/1907.01991v1
PDF	https://arxiv.org/pdf/1907.01991v1.pdf
PWC	https://paperswithcode.com/paper/circuit-based-intrinsic-methods-to-detect
Repo
Framework

Diagnosing Cardiac Abnormalities from 12-Lead Electrocardiograms Using Enhanced Deep Convolutional Neural Networks


Title	Diagnosing Cardiac Abnormalities from 12-Lead Electrocardiograms Using Enhanced Deep Convolutional Neural Networks
Authors	Binhang Yuan, Wenhui Xing
Abstract	We train an enhanced deep convolutional neural network in order to identify eight cardiac abnormalities from the standard 12-lead electrocardiograms (ECGs) using the dataset of 14000 ECGs. Instead of straightforwardly applying an end-to-end deep learning approach, we find that deep convolutional neural networks enhanced with sophisticated hand crafted features show advantages in reducing generalization errors. Additionally, data preprocessing and augmentation are essential since the distribution of eight cardiac abnormalities are highly biased in the given dataset. Our approach achieves promising generalization performance in the First China ECG Intelligent Competition; an empirical evaluation is also provided to validate the efficacy of our design on the competition ECG dataset.
Tasks
Published	2019-08-15
URL	https://arxiv.org/abs/1908.06802v1
PDF	https://arxiv.org/pdf/1908.06802v1.pdf
PWC	https://paperswithcode.com/paper/diagnosing-cardiac-abnormalities-from-12-lead
Repo
Framework

Embedded CNN based vehicle classification and counting in non-laned road traffic


Title	Embedded CNN based vehicle classification and counting in non-laned road traffic
Authors	Mayank Singh Chauhan, Arshdeep Singh, Mansi Khemka, Arneish Prateek, Rijurekha Sen
Abstract	Classifying and counting vehicles in road traffic has numerous applications in the transportation engineering domain. However, the wide variety of vehicles (two-wheelers, three-wheelers, cars, buses, trucks etc.) plying on roads of developing regions without any lane discipline, makes vehicle classification and counting a hard problem to automate. In this paper, we use state of the art Convolutional Neural Network (CNN) based object detection models and train them for multiple vehicle classes using data from Delhi roads. We get upto 75% MAP on an 80-20 train-test split using 5562 video frames from four different locations. As robust network connectivity is scarce in developing regions for continuous video transmissions from the road to cloud servers, we also evaluate the latency, energy and hardware cost of embedded implementations of our CNN model based inferences.
Tasks	Object Detection
Published	2019-01-18
URL	http://arxiv.org/abs/1901.06358v1
PDF	http://arxiv.org/pdf/1901.06358v1.pdf
PWC	https://paperswithcode.com/paper/embedded-cnn-based-vehicle-classification-and
Repo
Framework

Monitoring of people entering and exiting private areas using Computer Vision


Title	Monitoring of people entering and exiting private areas using Computer Vision
Authors	Vinay Kumar V, P Nagabhushan
Abstract	Entry-Exit surveillance is a novel research problem that addresses security concerns when people attain absolute privacy in camera forbidden areas such as toilets and changing rooms that are basic amenities to the humans in public places such as Shopping malls, Airports, Bus and Rail stations. The objective is, if not inside these camera forbidden areas, from outside, the individuals are to be monitored to analyze the time spent by them inside and also the suspecting transformations in their appearances if any. In this paper, firstly, a pseudo-annotated dataset of a laboratory observation of people entering and exiting the camera forbidden area captured using two cameras in contrast to the state-of-the-art single-camera based EnEx dataset is presented. Conventionally the proposed dataset is named \textbf{\textit{EnEx2}}. Next, a spatial transition based event detection to determine the entry or exit of individuals is presented with standard results by evaluating the proposed model using the proposed dataset and the publicly available standard video surveillance datasets that are hypothesized to Entry-Exit surveillance scenarios. The proposed dataset is expected to enkindle active research in Entry-Exit Surveillance domain.
Tasks
Published	2019-08-02
URL	https://arxiv.org/abs/1908.00716v2
PDF	https://arxiv.org/pdf/1908.00716v2.pdf
PWC	https://paperswithcode.com/paper/entry-exit-event-detection-and-learning
Repo
Framework