April 3, 2020

3112 words 15 mins read

Paper Group ANR 42

Paper Group ANR 42

Optimized Feature Space Learning for Generating Efficient Binary Codes for Image Retrieval. SOLAR: Second-Order Loss and Attention for Image Retrieval. GIQA: Generated Image Quality Assessment. Evaluation of Rounding Functions in Nearest-Neighbor Interpolation. Traffic Modelling and Prediction via Symbolic Regression on Road Sensor Data. Embedding …

Optimized Feature Space Learning for Generating Efficient Binary Codes for Image Retrieval

Title Optimized Feature Space Learning for Generating Efficient Binary Codes for Image Retrieval
Authors Abin Jose, Erik Stefan Ottlik, Christian Rohlfing, Jens-Rainer Ohm
Abstract In this paper we propose an approach for learning low dimensional optimized feature space with minimum intra-class variance and maximum inter-class variance. We address the problem of high-dimensionality of feature vectors extracted from neural networks by taking care of the global statistics of feature space. Classical approach of Linear Discriminant Analysis (LDA) is generally used for generating an optimized low dimensional feature space for single-labeled images. Since, image retrieval involves both multi-labeled and single-labeled images, we utilize the equivalence between LDA and Canonical Correlation Analysis (CCA) to generate an optimized feature space for single-labeled images and use CCA to generate an optimized feature space for multi-labeled images. Our approach correlates the projections of feature vectors with label vectors in our CCA based network architecture. The neural network minimize a loss function which maximizes the correlation coefficients. We binarize our generated feature vectors with the popular Iterative Quantization (ITQ) approach and also propose an ensemble network to generate binary codes of desired bit length for image retrieval. Our measurement of mean average precision shows competitive results on other state-of-the-art single-labeled and multi-labeled image retrieval datasets.
Tasks Image Retrieval, Quantization
Published 2020-01-30
URL https://arxiv.org/abs/2001.11400v1
PDF https://arxiv.org/pdf/2001.11400v1.pdf
PWC https://paperswithcode.com/paper/optimized-feature-space-learning-for

SOLAR: Second-Order Loss and Attention for Image Retrieval

Title SOLAR: Second-Order Loss and Attention for Image Retrieval
Authors Tony Ng, Vassileios Balntas, Yurun Tian, Krystian Mikolajczyk
Abstract Recent works in deep-learning have shown that utilising second-order information is beneficial in many computer-vision related tasks. Second-order information can be enforced both in the spatial context and the abstract feature dimensions. In this work we explore two second order components. One is focused on second-order spatial information to increase the performance of image descriptors, both local and global. More specifically, it is used to re-weight feature maps, and thus emphasise salient image locations that are subsequently used for description. The second component is concerned with a second-order similarity (SOS) loss, that we extend to global descriptors for image retrieval, and is used to enhance the triplet loss with hard negative mining. We validate our approach on two different tasks and three datasets for image retrieval and patch matching. The results show that our second order components bring significant performance improvements in both tasks and lead to state of the art results across the benchmarks.
Tasks Image Retrieval
Published 2020-01-24
URL https://arxiv.org/abs/2001.08972v3
PDF https://arxiv.org/pdf/2001.08972v3.pdf
PWC https://paperswithcode.com/paper/solar-second-order-loss-and-attention-for

GIQA: Generated Image Quality Assessment

Title GIQA: Generated Image Quality Assessment
Authors Shuyang Gu, Jianmin Bao, Dong Chen, Fang Wen
Abstract Generative adversarial networks (GANs) have achieved impressive results today, but not all generated images are perfect. A number of quantitative criteria have recently emerged for generative model, but none of them are designed for a single generated image. In this paper, we propose a new research topic, Generated Image Quality Assessment (GIQA), which quantitatively evaluates the quality of each generated image. We introduce three GIQA algorithms from two perspectives: learning-based and data-based. We evaluate a number of images generated by various recent GAN models on different datasets and demonstrate that they are consistent with human assessments. Furthermore, GIQA is available to many applications, like separately evaluating the realism and diversity of generative models, and enabling online hard negative mining (OHEM) in the training of GANs to improve the results.
Tasks Image Quality Assessment
Published 2020-03-19
URL https://arxiv.org/abs/2003.08932v1
PDF https://arxiv.org/pdf/2003.08932v1.pdf
PWC https://paperswithcode.com/paper/giqa-generated-image-quality-assessment

Evaluation of Rounding Functions in Nearest-Neighbor Interpolation

Title Evaluation of Rounding Functions in Nearest-Neighbor Interpolation
Authors Olivier Rukundo
Abstract This paper evaluates three rounding functions for nearest neighbor (NN) image interpolation. Evaluated rounding functions are selected among the five rounding rules defined by the IEEE 754-2008 standard. Both full- and non-reference image quality assessment (IQA) metrics evaluate interpolation image quality objectively to extract the number of achieved occurrences over targeted occurrences. Targeted occurrence indicates the optimally achievable number that is directly proportional to the number of sample images, IQA metrics, and scaling ratios. Inferential statistical analysis concept is applied to deduce from a small number of images and draw a conclusion of the behavior of each rounding function on a bigger number of images. Considering the number of images bigger than five, inferential analysis demonstrated that, at 95% of confidence level, the ceil function could also achieve 83.75% of targeted occurrences with 8 to 11% margin of error while the floor and round functions could only achieve 22.5% and 32.5% of targeted occurrences, respectively, with the same margin of error.
Tasks Image Quality Assessment
Published 2020-03-15
URL https://arxiv.org/abs/2003.06885v1
PDF https://arxiv.org/pdf/2003.06885v1.pdf
PWC https://paperswithcode.com/paper/evaluation-of-rounding-functions-in-nearest

Traffic Modelling and Prediction via Symbolic Regression on Road Sensor Data

Title Traffic Modelling and Prediction via Symbolic Regression on Road Sensor Data
Authors Alina Patelli, Victoria Lush, Aniko Ekart, Elisabeth Ilie-Zudor
Abstract The continuous expansion of the urban traffic sensing infrastructure has led to a surge in the volume of widely available road related data. Consequently, increasing effort is being dedicated to the creation of intelligent transportation systems, where decisions on issues ranging from city-wide road maintenance planning to improving the commuting experience are informed by computational models of urban traffic instead of being left entirely to humans. The automation of traffic management has received substantial attention from the research community, however, most approaches target highways, produce predictions valid for a limited time window or require expensive retraining of available models in order to accurately forecast traffic at a new location. In this article, we propose a novel and accurate traffic flow prediction method based on symbolic regression enhanced with a lag operator. Our approach produces robust models suitable for the intricacies of urban roads, much more difficult to predict than highways. Additionally, there is no need to retrain the model for a period of up to 9 weeks. Furthermore, the proposed method generates models that are transferable to other segments of the road network, similar to, yet geographically distinct from the ones they were initially trained on. We demonstrate the achievement of these claims by conducting extensive experiments on data collected from the Darmstadt urban infrastructure.
Published 2020-02-14
URL https://arxiv.org/abs/2002.06095v1
PDF https://arxiv.org/pdf/2002.06095v1.pdf
PWC https://paperswithcode.com/paper/traffic-modelling-and-prediction-via-symbolic

Embedding Compression with Isotropic Iterative Quantization

Title Embedding Compression with Isotropic Iterative Quantization
Authors Siyu Liao, Jie Chen, Yanzhi Wang, Qinru Qiu, Bo Yuan
Abstract Continuous representation of words is a standard component in deep learning-based NLP models. However, representing a large vocabulary requires significant memory, which can cause problems, particularly on resource-constrained platforms. Therefore, in this paper we propose an isotropic iterative quantization (IIQ) approach for compressing embedding vectors into binary ones, leveraging the iterative quantization technique well established for image retrieval, while satisfying the desired isotropic property of PMI based models. Experiments with pre-trained embeddings (i.e., GloVe and HDC) demonstrate a more than thirty-fold compression ratio with comparable and sometimes even improved performance over the original real-valued embedding vectors.
Tasks Image Retrieval, Quantization
Published 2020-01-11
URL https://arxiv.org/abs/2001.05314v2
PDF https://arxiv.org/pdf/2001.05314v2.pdf
PWC https://paperswithcode.com/paper/embedding-compression-with-isotropic

Approximating the Hotelling Observer with Autoencoder-Learned Efficient Channels for Binary Signal Detection Tasks

Title Approximating the Hotelling Observer with Autoencoder-Learned Efficient Channels for Binary Signal Detection Tasks
Authors Jason L. Granstedt, Weimin Zhou, Mark A. Anastasio
Abstract The objective assessment of image quality (IQ) has been advocated for the analysis and optimization of medical imaging systems. One method of obtaining such IQ metrics is through a mathematical observer. The Bayesian ideal observer is optimal by definition for signal detection tasks, but is frequently both intractable and non-linear. As an alternative, linear observers are sometimes used for task-based image quality assessment. The optimal linear observer is the Hotelling observer (HO). The computational cost of calculating the HO increases with image size, making a reduction in the dimensionality of the data desirable. Channelized methods have become popular for this purpose, and many competing methods are available for computing efficient channels. In this work, a novel method for learning channels using an autoencoder (AE) is presented. AEs are a type of artificial neural network (ANN) that are frequently employed to learn concise representations of data to reduce dimensionality. Modifying the traditional AE loss function to focus on task-relevant information permits the development of efficient AE-channels. These AE-channels were trained and tested on a variety of signal shapes and backgrounds to evaluate their performance. In the experiments, the AE-learned channels were competitive with and frequently outperformed other state-of-the-art methods for approximating the HO. The performance gains were greatest for the datasets with a small number of training images and noisy estimates of the signal image. Overall, AEs are demonstrated to be competitive with state-of-the-art methods for generating efficient channels for the HO and can have superior performance on small datasets.
Tasks Image Quality Assessment
Published 2020-03-04
URL https://arxiv.org/abs/2003.02321v1
PDF https://arxiv.org/pdf/2003.02321v1.pdf
PWC https://paperswithcode.com/paper/approximating-the-hotelling-observer-with

Learning Numerical Observers using Unsupervised Domain Adaptation

Title Learning Numerical Observers using Unsupervised Domain Adaptation
Authors Shenghua He, Weimin Zhou, Hua Li, Mark A. Anastasio
Abstract Medical imaging systems are commonly assessed by use of objective image quality measures. Supervised deep learning methods have been investigated to implement numerical observers for task-based image quality assessment. However, labeling large amounts of experimental data to train deep neural networks is tedious, expensive, and prone to subjective errors. Computer-simulated image data can potentially be employed to circumvent these issues; however, it is often difficult to computationally model complicated anatomical structures, noise sources, and the response of real world imaging systems. Hence, simulated image data will generally possess physical and statistical differences from the experimental image data they seek to emulate. Within the context of machine learning, these differences between the sets of two images is referred to as domain shift. In this study, we propose and investigate the use of an adversarial domain adaptation method to mitigate the deleterious effects of domain shift between simulated and experimental image data for deep learning-based numerical observers (DL-NOs) that are trained on simulated images but applied to experimental ones. In the proposed method, a DL-NO will initially be trained on computer-simulated image data and subsequently adapted for use with experimental image data, without the need for any labeled experimental images. As a proof of concept, a binary signal detection task is considered. The success of this strategy as a function of the degree of domain shift present between the simulated and experimental image data is investigated.
Tasks Domain Adaptation, Image Quality Assessment, Unsupervised Domain Adaptation
Published 2020-02-03
URL https://arxiv.org/abs/2002.03763v2
PDF https://arxiv.org/pdf/2002.03763v2.pdf
PWC https://paperswithcode.com/paper/learning-numerical-observers-using

Subjective Annotation for a Frame Interpolation Benchmark using Artifact Amplification

Title Subjective Annotation for a Frame Interpolation Benchmark using Artifact Amplification
Authors Hui Men, Vlad Hosu, Hanhe Lin, Andrés Bruhn, Dietmar Saupe
Abstract Current benchmarks for optical flow algorithms evaluate the estimation either directly by comparing the predicted flow fields with the ground truth or indirectly by using the predicted flow fields for frame interpolation and then comparing the interpolated frames with the actual frames. In the latter case, objective quality measures such as the mean squared error are typically employed. However, it is well known that for image quality assessment, the actual quality experienced by the user cannot be fully deduced from such simple measures. Hence, we conducted a subjective quality assessment crowdscouring study for the interpolated frames provided by one of the optical flow benchmarks, the Middlebury benchmark. It contains interpolated frames from 155 methods applied to each of 8 contents. We collected forced choice paired comparisons between interpolated images and corresponding ground truth. To increase the sensitivity of observers when judging minute difference in paired comparisons we introduced a new method to the field of full-reference quality assessment, called artifact amplification. From the crowdsourcing data we reconstructed absolute quality scale values according to Thurstone’s model. As a result, we obtained a re-ranking of the 155 participating algorithms w.r.t. the visual quality of the interpolated frames. This re-ranking not only shows the necessity of visual quality assessment as another evaluation metric for optical flow and frame interpolation benchmarks, the results also provide the ground truth for designing novel image quality assessment (IQA) methods dedicated to perceptual quality of interpolated images. As a first step, we proposed such a new full-reference method, called WAE-IQA. By weighing the local differences between an interpolated image and its ground truth WAE-IQA performed slightly better than the currently best FR-IQA approach from the literature.
Tasks Image Quality Assessment, Optical Flow Estimation
Published 2020-01-10
URL https://arxiv.org/abs/2001.06409v1
PDF https://arxiv.org/pdf/2001.06409v1.pdf
PWC https://paperswithcode.com/paper/subjective-annotation-for-a-frame

Unification-based Reconstruction of Explanations for Science Questions

Title Unification-based Reconstruction of Explanations for Science Questions
Authors Marco Valentino, Mokanarangan Thayaparan, André Freitas
Abstract The paper presents a framework to reconstruct explanations for multiple choices science questions through explanation-centred corpora. Building upon the notion of unification in science, the framework ranks explanatory facts with respect to question and candidate answer by leveraging a combination of two different scores: (a) A Relevance Score (RS) that represents the extent to which a given fact is specific to the question; (b) A Unification Score (US) that takes into account the explanatory power of a fact, determined according to its frequency in explanations for similar questions. An extensive evaluation of the framework is performed on the Worldtree corpus, adopting IR weighting schemes for its implementation. The following findings are presented: (1) The proposed approach achieves competitive results when compared to state-of-the-art Transformers, yet possessing the property of being scalable to large explanatory knowledge bases; (2) The combined model significantly outperforms IR baselines (+7.8/8.4 MAP), confirming the complementary aspects of relevance and unification score; (3) The constructed explanations can support downstream models for answer prediction, improving the accuracy of BERT for multiple choices QA on both ARC easy (+6.92%) and challenge (+15.69%) questions.
Published 2020-03-31
URL https://arxiv.org/abs/2004.00061v1
PDF https://arxiv.org/pdf/2004.00061v1.pdf
PWC https://paperswithcode.com/paper/unification-based-reconstruction-of

Construe: a software solution for the explanation-based interpretation of time series

Title Construe: a software solution for the explanation-based interpretation of time series
Authors Tomas Teijeiro, Paulo Felix
Abstract This paper presents a software implementation of a general framework for time series interpretation based on abductive reasoning. The software provides a data model and a set of algorithms to make inference to the best explanation of a time series, resulting in a description in multiple abstraction levels of the processes underlying the time series. As a proof of concept, a comprehensive knowledge base for the electrocardiogram (ECG) domain is provided, so it can be used directly as a tool for ECG analysis. This tool has been successfully validated in several noteworthy problems, such as heartbeat classification or atrial fibrillation detection.
Tasks Atrial Fibrillation Detection, Heartbeat Classification, Time Series
Published 2020-03-17
URL https://arxiv.org/abs/2003.07596v1
PDF https://arxiv.org/pdf/2003.07596v1.pdf
PWC https://paperswithcode.com/paper/construe-a-software-solution-for-the

Causality-based Explanation of Classification Outcomes

Title Causality-based Explanation of Classification Outcomes
Authors Leopoldo Bertossi, Jordan Li, Maximilian Schleich, Dan Suciu, Zografoula Vagena
Abstract We propose a simple definition of an explanation for the outcome of a classifier based on concepts from causality. We compare it with previously proposed notions of explanation, and study their complexity. We conduct an experimental evaluation with two real datasets from the financial domain.
Published 2020-03-15
URL https://arxiv.org/abs/2003.06868v1
PDF https://arxiv.org/pdf/2003.06868v1.pdf
PWC https://paperswithcode.com/paper/causality-based-explanation-of-classification

A Generalizable Knowledge Framework for Semantic Indoor Mapping Based on Markov Logic Networks and Data Driven MCMC

Title A Generalizable Knowledge Framework for Semantic Indoor Mapping Based on Markov Logic Networks and Data Driven MCMC
Authors Ziyuan Liu, Georg von Wichert
Abstract In this paper, we propose a generalizable knowledge framework for data abstraction, i.e. finding compact abstract model for input data using predefined abstract terms. Based on these abstract terms, intelligent autonomous systems, such as a robot, should be able to make inference according to specific knowledge base, so that they can better handle the complexity and uncertainty of the real world. We propose to realize this framework by combining Markov logic networks (MLNs) and data driven MCMC sampling, because the former are a powerful tool for modelling uncertain knowledge and the latter provides an efficient way to draw samples from unknown complex distributions. Furthermore, we show in detail how to adapt this framework to a certain task, in particular, semantic robot mapping. Based on MLNs, we formulate task-specific context knowledge as descriptive soft rules. Experiments on real world data and simulated data confirm the usefulness of our framework.
Published 2020-02-19
URL https://arxiv.org/abs/2002.08402v1
PDF https://arxiv.org/pdf/2002.08402v1.pdf
PWC https://paperswithcode.com/paper/a-generalizable-knowledge-framework-for

Forensic Scanner Identification Using Machine Learning

Title Forensic Scanner Identification Using Machine Learning
Authors Ruiting Shao, Edward J. Delp
Abstract Due to the increasing availability and functionality of image editing tools, many forensic techniques such as digital image authentication, source identification and tamper detection are important for forensic image analysis. In this paper, we describe a machine learning based system to address the forensic analysis of scanner devices. The proposed system uses deep-learning to automatically learn the intrinsic features from various scanned images. Our experimental results show that high accuracy can be achieved for source scanner identification. The proposed system can also generate a reliability map that indicates the manipulated regions in an scanned image.
Published 2020-02-06
URL https://arxiv.org/abs/2002.02079v1
PDF https://arxiv.org/pdf/2002.02079v1.pdf
PWC https://paperswithcode.com/paper/forensic-scanner-identification-using-machine

Finding online neural update rules by learning to remember

Title Finding online neural update rules by learning to remember
Authors Karol Gregor
Abstract We investigate learning of the online local update rules for neural activations (bodies) and weights (synapses) from scratch. We represent the states of each weight and activation by small vectors, and parameterize their updates using (meta-) neural networks. Different neuron types are represented by different embedding vectors which allows the same two functions to be used for all neurons. Instead of training directly for the objective using evolution or long term back-propagation, as is commonly done in similar systems, we motivate and study a different objective: That of remembering past snippets of experience. We explain how this objective relates to standard back-propagation training and other forms of learning. We train for this objective using short term back-propagation and analyze the performance as a function of both the different network types and the difficulty of the problem. We find that this analysis gives interesting insights onto what constitutes a learning rule. We also discuss how such system could form a natural substrate for addressing topics such as episodic memories, meta-learning and auxiliary objectives.
Tasks Meta-Learning
Published 2020-03-06
URL https://arxiv.org/abs/2003.03124v1
PDF https://arxiv.org/pdf/2003.03124v1.pdf
PWC https://paperswithcode.com/paper/finding-online-neural-update-rules-by
comments powered by Disqus