Paper Group ANR 189
A Comprehensive Benchmark for Single Image Compression Artifacts Reduction. A Policy Editor for Semantic Sensor Networks. Dense Recurrent Neural Networks for Inverse Problems: History-Cognizant Unrolling of Optimization Algorithms. Customized OCT images compression scheme with deep neural network. Statistical learnability of nuclear masses. Concord …
A Comprehensive Benchmark for Single Image Compression Artifacts Reduction
| Title | A Comprehensive Benchmark for Single Image Compression Artifacts Reduction |
| Authors | Jiaying Liu, Dong Liu, Wenhan Yang, Sifeng Xia, Xiaoshuai Zhang, Yuanying Dai |
| Abstract | We present a comprehensive study and evaluation of existing single image compression artifacts removal algorithms, using a new 4K resolution benchmark including diversified foreground objects and background scenes with rich structures, called Large-scale Ideal Ultra high definition 4K (LIU4K) benchmark. Compression artifacts removal, as a common post-processing technique, aims at alleviating undesirable artifacts such as blockiness, ringing, and banding caused by quantization and approximation in the compression process. In this work, a systematic listing of the reviewed methods is presented based on their basic models (handcrafted models and deep networks). The main contributions and novelties of these methods are highlighted, and the main development directions, including architectures, multi-domain sources, signal structures, and new targeted units, are summarized. Furthermore, based on a unified deep learning configuration (i.e. same training data, loss function, optimization algorithm, etc.), we evaluate recent deep learning-based methods based on diversified evaluation measures. The experimental results show the state-of-the-art performance comparison of existing methods based on both full-reference, non-reference and task-driven metrics. Our survey would give a comprehensive reference source for future research on single image compression artifacts removal and inspire new directions of the related fields. |
| Tasks | Image Compression, Quantization |
| Published | 2019-09-09 |
| URL | https://arxiv.org/abs/1909.03647v1 |
| https://arxiv.org/pdf/1909.03647v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-comprehensive-benchmark-for-single-image |
| Repo | |
| Framework | |
A Policy Editor for Semantic Sensor Networks
| Title | A Policy Editor for Semantic Sensor Networks |
| Authors | Paolo Pareti, George Konstantinidis, Timothy J. Norman |
| Abstract | An important use of sensors and actuator networks is to comply with health and safety policies in hazardous environments. In order to deal with increasingly large and dynamic environments, and to quickly react to emergencies, tools are needed to simplify the process of translating high-level policies into executable queries and rules. We present a framework to produce such tools, which uses rules to aggregate low-level sensor data, described using the Semantic Sensor Network Ontology, into more useful and actionable abstractions. Using the schema of the underlying data sources as an input, we automatically generate abstractions which are relevant to the use case at hand. In this demonstration we present a policy editor tool and a simulation on which policies can be tested. |
| Tasks | |
| Published | 2019-11-15 |
| URL | https://arxiv.org/abs/1911.06657v1 |
| https://arxiv.org/pdf/1911.06657v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-policy-editor-for-semantic-sensor-networks |
| Repo | |
| Framework | |
Dense Recurrent Neural Networks for Inverse Problems: History-Cognizant Unrolling of Optimization Algorithms
| Title | Dense Recurrent Neural Networks for Inverse Problems: History-Cognizant Unrolling of Optimization Algorithms |
| Authors | Seyed Amir Hossein Hosseini, Burhaneddin Yaman, Steen Moeller, Mingyi Hong, Mehmet Akçakaya |
| Abstract | Inverse problems in medical imaging applications incorporate domain-specific knowledge about the forward encoding operator in a regularized reconstruction framework. Recently physics-driven deep learning (DL) methods have been proposed to use neural networks for data-driven regularization. These methods unroll iterative optimization algorithms to solve the inverse problem objective function, by alternating between domain-specific data consistency and data-driven regularization via neural networks. The whole unrolled network is then trained end-to-end to learn the parameters of the network. Due to simplicity of data consistency updates with gradient descent steps, proximal gradient descent (PGD) is a common approach to unroll physics-driven DL reconstruction methods. However, PGD methods have slow convergence rates, necessitating a higher number of unrolled iterations, leading to memory issues in training and slower reconstruction times in testing. Inspired by efficient variants of PGD methods that use a history of the previous iterates, we propose a history-cognizant unrolling of the optimization algorithm with dense connections across iterations for improved performance. In our approach, the gradient descent steps are calculated at a trainable combination of the outputs of all the previous regularization units. We also apply this idea to unrolling variable splitting methods with quadratic relaxation. Our results in reconstruction of the fastMRI knee dataset show that the proposed history-cognizant approach reduces residual aliasing artifacts compared to its conventional unrolled counterpart without requiring extra computational power or increasing reconstruction time. |
| Tasks | |
| Published | 2019-12-16 |
| URL | https://arxiv.org/abs/1912.07197v1 |
| https://arxiv.org/pdf/1912.07197v1.pdf | |
| PWC | https://paperswithcode.com/paper/dense-recurrent-neural-networks-for-inverse |
| Repo | |
| Framework | |
Customized OCT images compression scheme with deep neural network
| Title | Customized OCT images compression scheme with deep neural network |
| Authors | Pengfei Guo, Dawei Li, Xingde Li |
| Abstract | We customize an end-to-end image compression framework for retina OCT images based on deep convolutional neural networks (CNNs). The customized compression scheme consists of three parts: data Preprocessing, compression CNNs, and reconstruction CNNs. Data preprocessing module reduces the speckle noise of the OCT images and the segments out the region of interest. We added customized skip connections between the compression CNNs and the reconstruction CNNs to reserve the detail information and trained the two nets together with the semantic segmented image patches from data preprocessing module. To train the two networks sensitive to both low frequency information and high frequency information, we adopted an objective function with two parts: A PatchGAN discriminator to judge the high frequency information and a differentiable MS-SSIM penalty to evaluate the low frequency information. The proposed framework was trained and evaluated on a publicly available OCT dataset. The evaluation showed above 99% similarity in terms of multi-scale structural similarity (MS-SSIM) when the compression ratio is as high as 40. Furthermore, the reconstructed images of compression ratio 80 from the proposed framework even have better quality than that of compression ratio 20 from JPEG by visual comparison. The testing result outperforms JPEG in term of both of MS-SSIM and visualization, which is more obvious as the increase of compression ratio. Our preliminary result indicates the huge potential of deep neural networks on customized medical image compression. |
| Tasks | Image Compression |
| Published | 2019-08-24 |
| URL | https://arxiv.org/abs/1908.09215v2 |
| https://arxiv.org/pdf/1908.09215v2.pdf | |
| PWC | https://paperswithcode.com/paper/customized-oct-images-compression-scheme-with |
| Repo | |
| Framework | |
Statistical learnability of nuclear masses
| Title | Statistical learnability of nuclear masses |
| Authors | Andrea Idini |
| Abstract | After more than 80 years from the seminal work of Weizs"acker and the liquid drop model of the atomic nucleus, deviations from experiments of mass models ($\sim$ MeV) are orders of magnitude larger than experimental errors ($\lesssim$ keV). Predicting the mass of atomic nuclei with precision is extremely challenging. This is due to the non–trivial many–body interplay of protons and neutrons in nuclei, and the complex nature of the nuclear strong force. Statistical theory of learning will be used to provide bounds to the prediction errors of model trained with a finite data set. These bounds are validated with neural network calculations, and compared with state of the art mass models. Therefore, it will be argued that the nuclear structure models investigating ground state properties explore a system on the limit of the knowledgeable, as defined by the statistical theory of learning. |
| Tasks | |
| Published | 2019-03-29 |
| URL | https://arxiv.org/abs/1904.00057v3 |
| https://arxiv.org/pdf/1904.00057v3.pdf | |
| PWC | https://paperswithcode.com/paper/pac-learnability-of-nuclear-masses |
| Repo | |
| Framework | |
Concordance probability in a big data setting: application in non-life insurance
| Title | Concordance probability in a big data setting: application in non-life insurance |
| Authors | Robin Van Oirbeek, Christopher Grumiau, Tim Verdonck |
| Abstract | The concordance probability or C-index is a popular measure to capture the discriminatory ability of a regression model. In this article, the definition of this measure is adapted to the specific needs of the frequency and severity model, typically used during the technical pricing of a non-life insurance product. Due to the typical large sample size of the frequency data in particular, two different adaptations of the estimation procedure of the concordance probability are presented. Note that the latter procedures can be applied to all different versions of the concordance probability. |
| Tasks | |
| Published | 2019-11-14 |
| URL | https://arxiv.org/abs/1911.06187v1 |
| https://arxiv.org/pdf/1911.06187v1.pdf | |
| PWC | https://paperswithcode.com/paper/concordance-probability-in-a-big-data-setting |
| Repo | |
| Framework | |
Collaborative Filtering vs. Content-Based Filtering: differences and similarities
| Title | Collaborative Filtering vs. Content-Based Filtering: differences and similarities |
| Authors | Rafael Glauber, Angelo Loula |
| Abstract | Recommendation Systems (SR) suggest items exploring user preferences, helping them with the information overload problem. Two approaches to SR have received more prominence, Collaborative Filtering, and Content-Based Filtering. Moreover, even though studies are indicating their advantages and disadvantages, few results empirically prove their characteristics, similarities, and differences. In this work, an experimental methodology is proposed to perform comparisons between recommendation algorithms for different approaches going beyond the “precision of the predictions”. For the experiments, three algorithms of recommendation were tested: a baseline for Collaborative Filtration and two algorithms for Content-based Filtering that were developed for this evaluation. The experiments demonstrate the behavior of these systems in different data sets, its main characteristics and especially the complementary aspect of the two main approaches. |
| Tasks | Recommendation Systems |
| Published | 2019-12-18 |
| URL | https://arxiv.org/abs/1912.08932v1 |
| https://arxiv.org/pdf/1912.08932v1.pdf | |
| PWC | https://paperswithcode.com/paper/collaborative-filtering-vs-content-based |
| Repo | |
| Framework | |
Zero-Shot Fine-Grained Style Transfer: Leveraging Distributed Continuous Style Representations to Transfer To Unseen Styles
| Title | Zero-Shot Fine-Grained Style Transfer: Leveraging Distributed Continuous Style Representations to Transfer To Unseen Styles |
| Authors | Eric Michael Smith, Diana Gonzalez-Rico, Emily Dinan, Y-Lan Boureau |
| Abstract | Text style transfer is usually performed using attributes that can take a handful of discrete values (e.g., positive to negative reviews). In this work, we introduce an architecture that can leverage pre-trained consistent continuous distributed style representations and use them to transfer to an attribute unseen during training, without requiring any re-tuning of the style transfer model. We demonstrate the method by training an architecture to transfer text conveying one sentiment to another sentiment, using a fine-grained set of over 20 sentiment labels rather than the binary positive/negative often used in style transfer. Our experiments show that this model can then rewrite text to match a target sentiment that was unseen during training. |
| Tasks | Style Transfer, Text Style Transfer |
| Published | 2019-11-10 |
| URL | https://arxiv.org/abs/1911.03914v1 |
| https://arxiv.org/pdf/1911.03914v1.pdf | |
| PWC | https://paperswithcode.com/paper/zero-shot-fine-grained-style-transfer |
| Repo | |
| Framework | |
Differentially Private Learning of Geometric Concepts
| Title | Differentially Private Learning of Geometric Concepts |
| Authors | Haim Kaplan, Yishay Mansour, Yossi Matias, Uri Stemmer |
| Abstract | We present differentially private efficient algorithms for learning union of polygons in the plane (which are not necessarily convex). Our algorithms achieve $(\alpha,\beta)$-PAC learning and $(\epsilon,\delta)$-differential privacy using a sample of size $\tilde{O}\left(\frac{1}{\alpha\epsilon}k\log d\right)$, where the domain is $[d]\times[d]$ and $k$ is the number of edges in the union of polygons. |
| Tasks | |
| Published | 2019-02-13 |
| URL | http://arxiv.org/abs/1902.05017v1 |
| http://arxiv.org/pdf/1902.05017v1.pdf | |
| PWC | https://paperswithcode.com/paper/differentially-private-learning-of-geometric |
| Repo | |
| Framework | |
Customized video filtering on YouTube
| Title | Customized video filtering on YouTube |
| Authors | Vishal Anand, Ravi Shukla, Ashwani Gupta, Abhishek Kumar |
| Abstract | Inappropriate and profane content on social media is exponentially increasing and big corporations are becoming more aware of the type of content on which they are advertising and how it may affect their brand reputation. But with a huge surge in content being posted online it becomes seemingly difficult to filter out related videos on which they can run their ads without compromising brand name. Advertising on youtube videos generates a huge amount of revenue for corporations. It becomes increasingly important for such corporations to advertise on only the videos that don’t hurt the feelings, community or harmony of the audience at large. In this paper, we propose a system to identify inappropriate content on YouTube and leverage it to perform a first of its kind, large scale, quantitative characterization that reveals some of the risks of YouTube ads consumption on inappropriate videos. Customization of the architecture have also been included to serve different requirements of corporations. Our analysis reveals that YouTube is still plagued by such disturbing videos and its currently deployed countermeasures are ineffective in terms of detecting them in a timely manner. Our framework tries to fill this gap by providing a handy, add on solution to filter the videos and help corporations and companies to push ads on the platform without worrying about the content on which the ads are displayed. |
| Tasks | |
| Published | 2019-11-11 |
| URL | https://arxiv.org/abs/1911.04013v2 |
| https://arxiv.org/pdf/1911.04013v2.pdf | |
| PWC | https://paperswithcode.com/paper/customized-video-filtering-on-youtube |
| Repo | |
| Framework | |
Automatic Table completion using Knowledge Base
| Title | Automatic Table completion using Knowledge Base |
| Authors | Bortik Bandyopadhyay, Xiang Deng, Goonmeet Bajaj, Huan Sun, Srinivasan Parthasarathy |
| Abstract | Table is a popular data format to organize and present relational information. Users often have to manually compose tables when gathering their desiderate information (e.g., entities and their attributes) for decision making. In this work, we propose to resolve a new type of heterogeneous query viz: tabular query, which contains a natural language query description, column names of the desired table, and an example row. We aim to acquire more entity tuples (rows) and automatically fill the table specified by the tabular query. We design a novel framework AutoTableComplete which aims to integrate schema specific structural information with the natural language contextual information provided by the user, to complete tables automatically, using a heterogeneous knowledge base (KB) as the main information source. Given a tabular query as input, our framework first constructs a set of candidate chains that connect the given example entities in KB. We learn to select the best matching chain from these candidates using the semantic context from tabular query. The selected chain is then converted into a SPARQL query, executed against KB to gather a set of candidate rows, that are then ranked in order of their relevance to the tabular query, to complete the desired table. We construct a new dataset based on tables in Wikipedia pages and Freebase, using which we perform a wide range of experiments to demonstrate the effectiveness of AutoTableComplete as well as present a detailed error analysis of our method. |
| Tasks | Decision Making |
| Published | 2019-09-20 |
| URL | https://arxiv.org/abs/1909.09565v1 |
| https://arxiv.org/pdf/1909.09565v1.pdf | |
| PWC | https://paperswithcode.com/paper/automatic-table-completion-using-knowledge |
| Repo | |
| Framework | |
An Underparametrized Deep Decoder Architecture for Graph Signals
| Title | An Underparametrized Deep Decoder Architecture for Graph Signals |
| Authors | Samuel Rey, Antonio G. Marques, Santiago Segarra |
| Abstract | While deep convolutional architectures have achieved remarkable results in a gamut of supervised applications dealing with images and speech, recent works show that deep untrained non-convolutional architectures can also outperform state-of-the-art methods in several tasks such as image compression and denoising. Motivated by the fact that many contemporary datasets have an irregular structure different from a 1D/2D grid, this paper generalizes untrained and underparametrized non-convolutional architectures to signals defined over irregular domains represented by graphs. The proposed architecture consists of a succession of layers, each of them implementing an upsampling operator, a linear feature combination, and a scalar nonlinearity. A novel element is the incorporation of upsampling operators accounting for the structure of the supporting graph, which is achieved by considering a systematic graph coarsening approach based on hierarchical clustering. The numerical results carried out in synthetic and real-world datasets showcase that the reconstruction performance can improve drastically if the information of the supporting graph topology is taken into account. |
| Tasks | Denoising, Image Compression |
| Published | 2019-08-02 |
| URL | https://arxiv.org/abs/1908.00878v2 |
| https://arxiv.org/pdf/1908.00878v2.pdf | |
| PWC | https://paperswithcode.com/paper/an-underparametrized-deep-decoder |
| Repo | |
| Framework | |
Deep Perceptual Compression
| Title | Deep Perceptual Compression |
| Authors | Yash Patel, Srikar Appalaraju, R. Manmatha |
| Abstract | Several deep learned lossy compression techniques have been proposed in the recent literature. Most of these are optimized by using either MS-SSIM (multi-scale structural similarity) or MSE (mean squared error) as a loss function. Unfortunately, neither of these correlate well with human perception and this is clearly visible from the resulting compressed images. In several cases, the MS-SSIM for deep learned techniques is higher than say a conventional, non-deep learned codec such as JPEG-2000 or BPG. However, the images produced by these deep learned techniques are in many cases clearly worse to human eyes than those produced by JPEG-2000 or BPG. We propose the use of an alternative, deep perceptual metric, which has been shown to align better with human perceptual similarity. We then propose Deep Perceptual Compression (DPC) which makes use of an encoder-decoder based image compression model to jointly optimize on the deep perceptual metric and MS-SSIM. Via extensive human evaluations, we show that the proposed method generates visually better results than previous learning based compression methods and JPEG-2000, and is comparable to BPG. Furthermore, we demonstrate that for tasks like object-detection, images compressed with DPC give better accuracy. |
| Tasks | Image Compression, Object Detection |
| Published | 2019-07-18 |
| URL | https://arxiv.org/abs/1907.08310v2 |
| https://arxiv.org/pdf/1907.08310v2.pdf | |
| PWC | https://paperswithcode.com/paper/deep-perceptual-compression |
| Repo | |
| Framework | |
A Universal Hierarchy of Shift-Stable Distributions and the Tradeoff Between Stability and Performance
| Title | A Universal Hierarchy of Shift-Stable Distributions and the Tradeoff Between Stability and Performance |
| Authors | Adarsh Subbaswamy, Bryant Chen, Suchi Saria |
| Abstract | Many methods which find invariant predictive distributions have been developed to learn models that can generalize to new environments without using samples from the target distribution. However, these methods consider differing types of shifts in environment and have been developed under disparate frameworks, making their comparison difficult. In this paper, we provide a unifying graphical representation of the data generating process that can represent all such shifts. We show there is a universal hierarchy of shift-stable distributions which correspond to operators on a graph that disable edges. This provides the ability to compare current methods and derive new algorithms that find optimal invariant distributions, all of which can be mapped to the hierarchy. We theoretically and empirically show that the degree to which stability is desirable depends on how concerned we are about large shifts: there is a tradeoff between stability and average performance. |
| Tasks | |
| Published | 2019-05-27 |
| URL | https://arxiv.org/abs/1905.11374v3 |
| https://arxiv.org/pdf/1905.11374v3.pdf | |
| PWC | https://paperswithcode.com/paper/should-i-include-this-edge-in-my-prediction |
| Repo | |
| Framework | |
Multi-Stream Single Shot Spatial-Temporal Action Detection
| Title | Multi-Stream Single Shot Spatial-Temporal Action Detection |
| Authors | Pengfei Zhang, Yu Cao, Benyuan Liu |
| Abstract | We present a 3D Convolutional Neural Networks (CNNs) based single shot detector for spatial-temporal action detection tasks. Our model includes: (1) two short-term appearance and motion streams, with single RGB and optical flow image input separately, in order to capture the spatial and temporal information for the current frame; (2) two long-term 3D ConvNet based stream, working on sequences of continuous RGB and optical flow images to capture the context from past frames. Our model achieves strong performance for action detection in video and can be easily integrated into any current two-stream action detection methods. We report a frame-mAP of 71.30% on the challenging UCF101-24 actions dataset, achieving the state-of-the-art result of the one-stage methods. To the best of our knowledge, our work is the first system that combined 3D CNN and SSD in action detection tasks. |
| Tasks | Action Detection, Optical Flow Estimation |
| Published | 2019-08-22 |
| URL | https://arxiv.org/abs/1908.08178v1 |
| https://arxiv.org/pdf/1908.08178v1.pdf | |
| PWC | https://paperswithcode.com/paper/multi-stream-single-shot-spatial-temporal |
| Repo | |
| Framework | |
