Paper Group ANR 133
Beyond Spatial Auto-Regressive Models: Predicting Housing Prices with Satellite Imagery. Self-Wiring Question Answering Systems. Flexible constrained sampling with guarantees for pattern mining. Hierarchy of Groups Evaluation Using Different F-score Variants. Low-Rank Representation over the Manifold of Curves. A Discriminative Framework for Anomal …
Beyond Spatial Auto-Regressive Models: Predicting Housing Prices with Satellite Imagery
| Title | Beyond Spatial Auto-Regressive Models: Predicting Housing Prices with Satellite Imagery |
| Authors | Archith J. Bency, Swati Rallapalli, Raghu K. Ganti, Mudhakar Srivatsa, B. S. Manjunath |
| Abstract | When modeling geo-spatial data, it is critical to capture spatial correlations for achieving high accuracy. Spatial Auto-Regression (SAR) is a common tool used to model such data, where the spatial contiguity matrix (W) encodes the spatial correlations. However, the efficacy of SAR is limited by two factors. First, it depends on the choice of contiguity matrix, which is typically not learnt from data, but instead, is assumed to be known apriori. Second, it assumes that the observations can be explained by linear models. In this paper, we propose a Convolutional Neural Network (CNN) framework to model geo-spatial data (specifi- cally housing prices), to learn the spatial correlations automatically. We show that neighborhood information embedded in satellite imagery can be leveraged to achieve the desired spatial smoothing. An additional upside of our framework is the relaxation of linear assumption on the data. Specific challenges we tackle while implementing our framework include, (i) how much of the neighborhood is relevant while estimating housing prices? (ii) what is the right approach to capture multiple resolutions of satellite imagery? and (iii) what other data-sources can help improve the estimation of spatial correlations? We demonstrate a marked improvement of 57% on top of the SAR baseline through the use of features from deep neural networks for the cities of London, Birmingham and Liverpool. |
| Tasks | |
| Published | 2016-10-16 |
| URL | http://arxiv.org/abs/1610.04805v1 |
| http://arxiv.org/pdf/1610.04805v1.pdf | |
| PWC | https://paperswithcode.com/paper/beyond-spatial-auto-regressive-models |
| Repo | |
| Framework | |
Self-Wiring Question Answering Systems
| Title | Self-Wiring Question Answering Systems |
| Authors | Ricardo Usbeck, Jonathan Huthmann, Nico Duldhardt, Axel-Cyrille Ngonga Ngomo |
| Abstract | Question answering (QA) has been the subject of a resurgence over the past years. The said resurgence has led to a multitude of question answering (QA) systems being developed both by companies and research facilities. While a few components of QA systems get reused across implementations, most systems do not leverage the full potential of component reuse. Hence, the development of QA systems is currently still a tedious and time-consuming process. We address the challenge of accelerating the creation of novel or tailored QA systems by presenting a concept for a self-wiring approach to composing QA systems. Our approach will allow the reuse of existing, web-based QA systems or modules while developing new QA platforms. To this end, it will rely on QA modules being described using the Web Ontology Language. Based on these descriptions, our approach will be able to automatically compose QA systems using a data-driven approach automatically. |
| Tasks | Question Answering |
| Published | 2016-11-06 |
| URL | http://arxiv.org/abs/1611.01802v2 |
| http://arxiv.org/pdf/1611.01802v2.pdf | |
| PWC | https://paperswithcode.com/paper/self-wiring-question-answering-systems |
| Repo | |
| Framework | |
Flexible constrained sampling with guarantees for pattern mining
| Title | Flexible constrained sampling with guarantees for pattern mining |
| Authors | Vladimir Dzyuba, Matthijs van Leeuwen, Luc De Raedt |
| Abstract | Pattern sampling has been proposed as a potential solution to the infamous pattern explosion. Instead of enumerating all patterns that satisfy the constraints, individual patterns are sampled proportional to a given quality measure. Several sampling algorithms have been proposed, but each of them has its limitations when it comes to 1) flexibility in terms of quality measures and constraints that can be used, and/or 2) guarantees with respect to sampling accuracy. We therefore present Flexics, the first flexible pattern sampler that supports a broad class of quality measures and constraints, while providing strong guarantees regarding sampling accuracy. To achieve this, we leverage the perspective on pattern mining as a constraint satisfaction problem and build upon the latest advances in sampling solutions in SAT as well as existing pattern mining algorithms. Furthermore, the proposed algorithm is applicable to a variety of pattern languages, which allows us to introduce and tackle the novel task of sampling sets of patterns. We introduce and empirically evaluate two variants of Flexics: 1) a generic variant that addresses the well-known itemset sampling task and the novel pattern set sampling task as well as a wide range of expressive constraints within these tasks, and 2) a specialized variant that exploits existing frequent itemset techniques to achieve substantial speed-ups. Experiments show that Flexics is both accurate and efficient, making it a useful tool for pattern-based data exploration. |
| Tasks | |
| Published | 2016-10-28 |
| URL | http://arxiv.org/abs/1610.09263v2 |
| http://arxiv.org/pdf/1610.09263v2.pdf | |
| PWC | https://paperswithcode.com/paper/flexible-constrained-sampling-with-guarantees |
| Repo | |
| Framework | |
Hierarchy of Groups Evaluation Using Different F-score Variants
| Title | Hierarchy of Groups Evaluation Using Different F-score Variants |
| Authors | Michał Spytkowski, Łukasz P. Olech, Halina Kwaśnicka |
| Abstract | The paper presents a cursory examination of clustering, focusing on a rarely explored field of hierarchy of clusters. Based on this, a short discussion of clustering quality measures is presented and the F-score measure is examined more deeply. As there are no attempts to assess the quality for hierarchies of clusters, three variants of the F-Score based index are presented: classic, hierarchical and partial order. The partial order index is the authors’ approach to the subject. Conducted experiments show the properties of the considered measures. In conclusions, the strong and weak sides of each variant are presented. |
| Tasks | |
| Published | 2016-03-28 |
| URL | http://arxiv.org/abs/1603.08323v1 |
| http://arxiv.org/pdf/1603.08323v1.pdf | |
| PWC | https://paperswithcode.com/paper/hierarchy-of-groups-evaluation-using |
| Repo | |
| Framework | |
Low-Rank Representation over the Manifold of Curves
| Title | Low-Rank Representation over the Manifold of Curves |
| Authors | Stephen Tierney, Junbin Gao, Yi Guo, Zhengwu Zhang |
| Abstract | In machine learning it is common to interpret each data point as a vector in Euclidean space. However the data may actually be functional i.e.\ each data point is a function of some variable such as time and the function is discretely sampled. The naive treatment of functional data as traditional multivariate data can lead to poor performance since the algorithms are ignoring the correlation in the curvature of each function. In this paper we propose a method to analyse subspace structure of the functional data by using the state of the art Low-Rank Representation (LRR). Experimental evaluation on synthetic and real data reveals that this method massively outperforms conventional LRR in tasks concerning functional data. |
| Tasks | |
| Published | 2016-01-05 |
| URL | http://arxiv.org/abs/1601.00732v2 |
| http://arxiv.org/pdf/1601.00732v2.pdf | |
| PWC | https://paperswithcode.com/paper/low-rank-representation-over-the-manifold-of |
| Repo | |
| Framework | |
A Discriminative Framework for Anomaly Detection in Large Videos
| Title | A Discriminative Framework for Anomaly Detection in Large Videos |
| Authors | Allison Del Giorno, J. Andrew Bagnell, Martial Hebert |
| Abstract | We address an anomaly detection setting in which training sequences are unavailable and anomalies are scored independently of temporal ordering. Current algorithms in anomaly detection are based on the classical density estimation approach of learning high-dimensional models and finding low-probability events. These algorithms are sensitive to the order in which anomalies appear and require either training data or early context assumptions that do not hold for longer, more complex videos. By defining anomalies as examples that can be distinguished from other examples in the same video, our definition inspires a shift in approaches from classical density estimation to simple discriminative learning. Our contributions include a novel framework for anomaly detection that is (1) independent of temporal ordering of anomalies, and (2) unsupervised, requiring no separate training sequences. We show that our algorithm can achieve state-of-the-art results even when we adjust the setting by removing training sequences from standard datasets. |
| Tasks | Anomaly Detection, Density Estimation |
| Published | 2016-09-28 |
| URL | http://arxiv.org/abs/1609.08938v1 |
| http://arxiv.org/pdf/1609.08938v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-discriminative-framework-for-anomaly |
| Repo | |
| Framework | |
Label Tree Embeddings for Acoustic Scene Classification
| Title | Label Tree Embeddings for Acoustic Scene Classification |
| Authors | Huy Phan, Lars Hertel, Marco Maass, Philipp Koch, Alfred Mertins |
| Abstract | We present in this paper an efficient approach for acoustic scene classification by exploring the structure of class labels. Given a set of class labels, a category taxonomy is automatically learned by collectively optimizing a clustering of the labels into multiple meta-classes in a tree structure. An acoustic scene instance is then embedded into a low-dimensional feature representation which consists of the likelihoods that it belongs to the meta-classes. We demonstrate state-of-the-art results on two different datasets for the acoustic scene classification task, including the DCASE 2013 and LITIS Rouen datasets. |
| Tasks | Acoustic Scene Classification, Scene Classification |
| Published | 2016-06-25 |
| URL | http://arxiv.org/abs/1606.07908v2 |
| http://arxiv.org/pdf/1606.07908v2.pdf | |
| PWC | https://paperswithcode.com/paper/label-tree-embeddings-for-acoustic-scene |
| Repo | |
| Framework | |
Deep Colorization
| Title | Deep Colorization |
| Authors | Zezhou Cheng, Qingxiong Yang, Bin Sheng |
| Abstract | This paper investigates into the colorization problem which converts a grayscale image to a colorful version. This is a very difficult problem and normally requires manual adjustment to achieve artifact-free quality. For instance, it normally requires human-labelled color scribbles on the grayscale target image or a careful selection of colorful reference images (e.g., capturing the same scene in the grayscale target image). Unlike the previous methods, this paper aims at a high-quality fully-automatic colorization method. With the assumption of a perfect patch matching technique, the use of an extremely large-scale reference database (that contains sufficient color images) is the most reliable solution to the colorization problem. However, patch matching noise will increase with respect to the size of the reference database in practice. Inspired by the recent success in deep learning techniques which provide amazing modeling of large-scale data, this paper re-formulates the colorization problem so that deep learning techniques can be directly employed. To ensure artifact-free quality, a joint bilateral filtering based post-processing step is proposed. We further develop an adaptive image clustering technique to incorporate the global image information. Numerous experiments demonstrate that our method outperforms the state-of-art algorithms both in terms of quality and speed. |
| Tasks | Colorization, Image Clustering |
| Published | 2016-04-30 |
| URL | http://arxiv.org/abs/1605.00075v1 |
| http://arxiv.org/pdf/1605.00075v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-colorization |
| Repo | |
| Framework | |
Rolling Horizon Coevolutionary Planning for Two-Player Video Games
| Title | Rolling Horizon Coevolutionary Planning for Two-Player Video Games |
| Authors | Jialin Liu, Diego Pérez-Liébana, Simon M. Lucas |
| Abstract | This paper describes a new algorithm for decision making in two-player real-time video games. As with Monte Carlo Tree Search, the algorithm can be used without heuristics and has been developed for use in general video game AI. The approach is to extend recent work on rolling horizon evolutionary planning, which has been shown to work well for single-player games, to two (or in principle many) player games. To select an action the algorithm co-evolves two (or in the general case N) populations, one for each player, where each individual is a sequence of actions for the respective player. The fitness of each individual is evaluated by playing it against a selection of action-sequences from the opposing population. When choosing an action to take in the game, the first action is chosen from the fittest member of the population for that player. The new algorithm is compared with a number of general video game AI algorithms on three variations of a two-player space battle game, with promising results. |
| Tasks | Decision Making |
| Published | 2016-07-06 |
| URL | http://arxiv.org/abs/1607.01730v1 |
| http://arxiv.org/pdf/1607.01730v1.pdf | |
| PWC | https://paperswithcode.com/paper/rolling-horizon-coevolutionary-planning-for |
| Repo | |
| Framework | |
Surprisal-Driven Feedback in Recurrent Networks
| Title | Surprisal-Driven Feedback in Recurrent Networks |
| Authors | Kamil M Rocki |
| Abstract | Recurrent neural nets are widely used for predicting temporal data. Their inherent deep feedforward structure allows learning complex sequential patterns. It is believed that top-down feedback might be an important missing ingredient which in theory could help disambiguate similar patterns depending on broader context. In this paper we introduce surprisal-driven recurrent networks, which take into account past error information when making new predictions. This is achieved by continuously monitoring the discrepancy between most recent predictions and the actual observations. Furthermore, we show that it outperforms other stochastic and fully deterministic approaches on enwik8 character level prediction task achieving 1.37 BPC on the test portion of the text. |
| Tasks | |
| Published | 2016-08-22 |
| URL | http://arxiv.org/abs/1608.06027v4 |
| http://arxiv.org/pdf/1608.06027v4.pdf | |
| PWC | https://paperswithcode.com/paper/surprisal-driven-feedback-in-recurrent |
| Repo | |
| Framework | |
Discriminating image textures with the multiscale two-dimensional complexity-entropy causality plane
| Title | Discriminating image textures with the multiscale two-dimensional complexity-entropy causality plane |
| Authors | Luciano Zunino, Haroldo V. Ribeiro |
| Abstract | The aim of this paper is to further explore the usefulness of the two-dimensional complexity-entropy causality plane as a texture image descriptor. A multiscale generalization is introduced in order to distinguish between different roughness features of images at small and large spatial scales. Numerically generated two-dimensional structures are initially considered for illustrating basic concepts in a controlled framework. Then, more realistic situations are studied. Obtained results allow us to confirm that intrinsic spatial correlations of images are successfully unveiled by implementing this multiscale symbolic information-theory approach. Consequently, we conclude that the proposed representation space is a versatile and practical tool for identifying, characterizing and discriminating image textures. |
| Tasks | |
| Published | 2016-09-06 |
| URL | http://arxiv.org/abs/1609.01625v2 |
| http://arxiv.org/pdf/1609.01625v2.pdf | |
| PWC | https://paperswithcode.com/paper/discriminating-image-textures-with-the |
| Repo | |
| Framework | |
MUG: A Parameterless No-Reference JPEG Quality Evaluator Robust to Block Size and Misalignment
| Title | MUG: A Parameterless No-Reference JPEG Quality Evaluator Robust to Block Size and Misalignment |
| Authors | Hossein Ziaei Nafchi, Atena Shahkolaei, Rachid Hedjam, Mohamed Cheriet |
| Abstract | In this letter, a very simple no-reference image quality assessment (NR-IQA) model for JPEG compressed images is proposed. The proposed metric called median of unique gradients (MUG) is based on the very simple facts of unique gradient magnitudes of JPEG compressed images. MUG is a parameterless metric and does not need training. Unlike other NR-IQAs, MUG is independent to block size and cropping. A more stable index called MUG+ is also introduced. The experimental results on six benchmark datasets of natural images and a benchmark dataset of synthetic images show that MUG is comparable to the state-of-the-art indices in literature. In addition, its performance remains unchanged for the case of the cropped images in which block boundaries are not known. The MATLAB source code of the proposed metrics is available at https://dl.dropboxusercontent.com/u/74505502/MUG.m and https://dl.dropboxusercontent.com/u/74505502/MUGplus.m. |
| Tasks | Image Quality Assessment, No-Reference Image Quality Assessment |
| Published | 2016-09-12 |
| URL | http://arxiv.org/abs/1609.03461v2 |
| http://arxiv.org/pdf/1609.03461v2.pdf | |
| PWC | https://paperswithcode.com/paper/mug-a-parameterless-no-reference-jpeg-quality |
| Repo | |
| Framework | |
Automated Breast Lesion Segmentation in Ultrasound Images
| Title | Automated Breast Lesion Segmentation in Ultrasound Images |
| Authors | Ibrahim Sadek, Mohamed Elawady, Viktor Stefanovski |
| Abstract | The main objective of this project is to segment different breast ultrasound images to find out lesion area by discarding the low contrast regions as well as the inherent speckle noise. The proposed method consists of three stages (removing noise, segmentation, classification) in order to extract the correct lesion. We used normalized cuts approach to segment ultrasound images into regions of interest where we can possibly finds the lesion, and then K-means classifier is applied to decide finally the location of the lesion. For every original image, an annotated ground-truth image is given to perform comparison with the obtained experimental results, providing accurate evaluation measures. |
| Tasks | Lesion Segmentation |
| Published | 2016-09-27 |
| URL | http://arxiv.org/abs/1609.08364v1 |
| http://arxiv.org/pdf/1609.08364v1.pdf | |
| PWC | https://paperswithcode.com/paper/automated-breast-lesion-segmentation-in |
| Repo | |
| Framework | |
Skin Lesion Analysis toward Melanoma Detection: A Challenge at the International Symposium on Biomedical Imaging (ISBI) 2016, hosted by the International Skin Imaging Collaboration (ISIC)
| Title | Skin Lesion Analysis toward Melanoma Detection: A Challenge at the International Symposium on Biomedical Imaging (ISBI) 2016, hosted by the International Skin Imaging Collaboration (ISIC) |
| Authors | David Gutman, Noel C. F. Codella, Emre Celebi, Brian Helba, Michael Marchetti, Nabin Mishra, Allan Halpern |
| Abstract | In this article, we describe the design and implementation of a publicly accessible dermatology image analysis benchmark challenge. The goal of the challenge is to sup- port research and development of algorithms for automated diagnosis of melanoma, a lethal form of skin cancer, from dermoscopic images. The challenge was divided into sub-challenges for each task involved in image analysis, including lesion segmentation, dermoscopic feature detection within a lesion, and classification of melanoma. Training data included 900 images. A separate test dataset of 379 images was provided to measure resultant performance of systems developed with the training data. Ground truth for both training and test sets was generated by a panel of dermoscopic experts. In total, there were 79 submissions from a group of 38 participants, making this the largest standardized and comparative study for melanoma diagnosis in dermoscopic images to date. While the official challenge duration and ranking of participants has concluded, the datasets remain available for further research and development. |
| Tasks | Lesion Segmentation |
| Published | 2016-05-04 |
| URL | http://arxiv.org/abs/1605.01397v1 |
| http://arxiv.org/pdf/1605.01397v1.pdf | |
| PWC | https://paperswithcode.com/paper/skin-lesion-analysis-toward-melanoma-2 |
| Repo | |
| Framework | |
An Overview of Melanoma Detection in Dermoscopy Images Using Image Processing and Machine Learning
| Title | An Overview of Melanoma Detection in Dermoscopy Images Using Image Processing and Machine Learning |
| Authors | Nabin K. Mishra, M. Emre Celebi |
| Abstract | The incidence of malignant melanoma continues to increase worldwide. This cancer can strike at any age; it is one of the leading causes of loss of life in young persons. Since this cancer is visible on the skin, it is potentially detectable at a very early stage when it is curable. New developments have converged to make fully automatic early melanoma detection a real possibility. First, the advent of dermoscopy has enabled a dramatic boost in clinical diagnostic ability to the point that melanoma can be detected in the clinic at the very earliest stages. The global adoption of this technology has allowed accumulation of large collections of dermoscopy images of melanomas and benign lesions validated by histopathology. The development of advanced technologies in the areas of image processing and machine learning have given us the ability to allow distinction of malignant melanoma from the many benign mimics that require no biopsy. These new technologies should allow not only earlier detection of melanoma, but also reduction of the large number of needless and costly biopsy procedures. Although some of the new systems reported for these technologies have shown promise in preliminary trials, widespread implementation must await further technical progress in accuracy and reproducibility. In this paper, we provide an overview of computerized detection of melanoma in dermoscopy images. First, we discuss the various aspects of lesion segmentation. Then, we provide a brief overview of clinical feature segmentation. Finally, we discuss the classification stage where machine learning algorithms are applied to the attributes generated from the segmented features to predict the existence of melanoma. |
| Tasks | Lesion Segmentation |
| Published | 2016-01-28 |
| URL | http://arxiv.org/abs/1601.07843v1 |
| http://arxiv.org/pdf/1601.07843v1.pdf | |
| PWC | https://paperswithcode.com/paper/an-overview-of-melanoma-detection-in |
| Repo | |
| Framework | |
