Paper Group ANR 335
Saliency-Enhanced Robust Visual Tracking. Modelling local phase of images and textures with applications in phase denoising and phase retrieval. The Training of Neuromodels for Machine Comprehension of Text. Brain2Text Algorithm. Effective Occlusion Handling for Fast Correlation Filter-based Trackers. Dual Conditional Cross-Entropy Filtering of Noi …
Saliency-Enhanced Robust Visual Tracking
| Title | Saliency-Enhanced Robust Visual Tracking |
| Authors | Caglar Aytekin, Francesco Cricri, Emre Aksu |
| Abstract | Discrete correlation filter (DCF) based trackers have shown considerable success in visual object tracking. These trackers often make use of low to mid level features such as histogram of gradients (HoG) and mid-layer activations from convolution neural networks (CNNs). We argue that including semantically higher level information to the tracked features may provide further robustness to challenging cases such as viewpoint changes. Deep salient object detection is one example of such high level features, as it make use of semantic information to highlight the important regions in the given scene. In this work, we propose an improvement over DCF based trackers by combining saliency based and other features based filter responses. This combination is performed with an adaptive weight on the saliency based filter responses, which is automatically selected according to the temporal consistency of visual saliency. We show that our method consistently improves a baseline DCF based tracker especially in challenging cases and performs superior to the state-of-the-art. Our improved tracker operates at 9.3 fps, introducing a small computational burden over the baseline which operates at 11 fps. |
| Tasks | Object Detection, Object Tracking, Salient Object Detection, Visual Object Tracking, Visual Tracking |
| Published | 2018-02-08 |
| URL | http://arxiv.org/abs/1802.02783v1 |
| http://arxiv.org/pdf/1802.02783v1.pdf | |
| PWC | https://paperswithcode.com/paper/saliency-enhanced-robust-visual-tracking |
| Repo | |
| Framework | |
Modelling local phase of images and textures with applications in phase denoising and phase retrieval
| Title | Modelling local phase of images and textures with applications in phase denoising and phase retrieval |
| Authors | Ido Zachevsky, Yehoshua Y. Zeevi |
| Abstract | The Fourier magnitude has been studied extensively, but less effort has been devoted to the Fourier phase, despite its well-established importance in image representation. Global phase was shown to be more important for image representation than the magnitude, whereas local phase, exhibited in Gabor filters, has been used for analysis purposes in detecting image contours and edges. Neither global nor local phase has been modelled in closed form, suitable for Bayesian estimation. In this work, we analyze the local phase of textured images and propose a local (Markovian) model for local phase coefficients. This model is Gaussian-mixture-based, learned from the graph representation of images, based on their complex wavelet decomposition. We demonstrate the applicability of the model in restoration of images with noisy local phase and in image retrieval, where we show superior performance to the well-known hybrid input-output (HIO) method. We also provide a framework for application of the model in a general setup of image processing. |
| Tasks | Denoising, Image Retrieval |
| Published | 2018-09-30 |
| URL | http://arxiv.org/abs/1810.00403v1 |
| http://arxiv.org/pdf/1810.00403v1.pdf | |
| PWC | https://paperswithcode.com/paper/modelling-local-phase-of-images-and-textures |
| Repo | |
| Framework | |
The Training of Neuromodels for Machine Comprehension of Text. Brain2Text Algorithm
| Title | The Training of Neuromodels for Machine Comprehension of Text. Brain2Text Algorithm |
| Authors | A. Artemov, A. Sergeev, A. Khasenevich, A. Yuzhakov, M. Chugunov |
| Abstract | Nowadays, the Internet represents a vast informational space, growing exponentially and the problem of search for relevant data becomes essential as never before. The algorithm proposed in the article allows to perform natural language queries on content of the document and get comprehensive meaningful answers. The problem is partially solved for English as SQuAD contains enough data to learn on, but there is no such dataset in Russian, so the methods used by scientists now are not applicable to Russian. Brain2 framework allows to cope with the problem - it stands out for its ability to be applied on small datasets and does not require impressive computing power. The algorithm is illustrated on Sberbank of Russia Strategy’s text and assumes the use of a neuromodel consisting of 65 mln synapses. The trained model is able to construct word-by-word answers to questions based on a given text. The existing limitations are its current inability to identify synonyms, pronoun relations and allegories. Nevertheless, the results of conducted experiments showed high capacity and generalisation ability of the suggested approach. |
| Tasks | Reading Comprehension |
| Published | 2018-03-30 |
| URL | http://arxiv.org/abs/1804.00551v1 |
| http://arxiv.org/pdf/1804.00551v1.pdf | |
| PWC | https://paperswithcode.com/paper/the-training-of-neuromodels-for-machine |
| Repo | |
| Framework | |
Effective Occlusion Handling for Fast Correlation Filter-based Trackers
| Title | Effective Occlusion Handling for Fast Correlation Filter-based Trackers |
| Authors | Zheng Zhang, Yang Li, Jinwei Ren, Jianke Zhu |
| Abstract | Correlation filter-based trackers heavily suffer from the problem of multiple peaks in their response maps incurred by occlusions. Moreover, the whole tracking pipeline may break down due to the uncertainties brought by shifting among peaks, which will further lead to the degraded correlation filter model. To alleviate the drift problem caused by occlusions, we propose a novel scheme to choose the specific filter model according to different scenarios. Specifically, an effective measurement function is designed to evaluate the quality of filter response. A sophisticated strategy is employed to judge whether occlusions occur, and then decide how to update the filter models. In addition, we take advantage of both log-polar method and pyramid-like approach to estimate the best scale of the target. We evaluate our proposed approach on VOT2018 challenge and OTB100 dataset, whose experimental result shows that the proposed tracker achieves the promising performance compared against the state-of-the-art trackers. |
| Tasks | |
| Published | 2018-07-13 |
| URL | http://arxiv.org/abs/1807.04880v1 |
| http://arxiv.org/pdf/1807.04880v1.pdf | |
| PWC | https://paperswithcode.com/paper/effective-occlusion-handling-for-fast |
| Repo | |
| Framework | |
Dual Conditional Cross-Entropy Filtering of Noisy Parallel Corpora
| Title | Dual Conditional Cross-Entropy Filtering of Noisy Parallel Corpora |
| Authors | Marcin Junczys-Dowmunt |
| Abstract | In this work we introduce dual conditional cross-entropy filtering for noisy parallel data. For each sentence pair of the noisy parallel corpus we compute cross-entropy scores according to two inverse translation models trained on clean data. We penalize divergent cross-entropies and weigh the penalty by the cross-entropy average of both models. Sorting or thresholding according to these scores results in better subsets of parallel data. We achieve higher BLEU scores with models trained on parallel data filtered only from Paracrawl than with models trained on clean WMT data. We further evaluate our method in the context of the WMT2018 shared task on parallel corpus filtering and achieve the overall highest ranking scores of the shared task, scoring top in three out of four subtasks. |
| Tasks | |
| Published | 2018-09-01 |
| URL | http://arxiv.org/abs/1809.00197v2 |
| http://arxiv.org/pdf/1809.00197v2.pdf | |
| PWC | https://paperswithcode.com/paper/dual-conditional-cross-entropy-filtering-of |
| Repo | |
| Framework | |
Sentiment Analysis of Financial News Articles using Performance Indicators
| Title | Sentiment Analysis of Financial News Articles using Performance Indicators |
| Authors | Srikumar Krishnamoorthy |
| Abstract | Mining financial text documents and understanding the sentiments of individual investors, institutions and markets is an important and challenging problem in the literature. Current approaches to mine sentiments from financial texts largely rely on domain specific dictionaries. However, dictionary based methods often fail to accurately predict the polarity of financial texts. This paper aims to improve the state-of-the-art and introduces a novel sentiment analysis approach that employs the concept of financial and non-financial performance indicators. It presents an association rule mining based hierarchical sentiment classifier model to predict the polarity of financial texts as positive, neutral or negative. The performance of the proposed model is evaluated on a benchmark financial dataset. The model is also compared against other state-of-the-art dictionary and machine learning based approaches and the results are found to be quite promising. The novel use of performance indicators for financial sentiment analysis offers interesting and useful insights. |
| Tasks | Sentiment Analysis |
| Published | 2018-11-25 |
| URL | http://arxiv.org/abs/1811.11008v1 |
| http://arxiv.org/pdf/1811.11008v1.pdf | |
| PWC | https://paperswithcode.com/paper/sentiment-analysis-of-financial-news-articles |
| Repo | |
| Framework | |
Effective Feature Representation for Clinical Text Concept Extraction
| Title | Effective Feature Representation for Clinical Text Concept Extraction |
| Authors | Yifeng Tao, Bruno Godefroy, Guillaume Genthial, Christopher Potts |
| Abstract | Crucial information about the practice of healthcare is recorded only in free-form text, which creates an enormous opportunity for high-impact NLP. However, annotated healthcare datasets tend to be small and expensive to obtain, which raises the question of how to make maximally efficient uses of the available data. To this end, we develop an LSTM-CRF model for combining unsupervised word representations and hand-built feature representations derived from publicly available healthcare ontologies. We show that this combined model yields superior performance on five datasets of diverse kinds of healthcare text (clinical, social, scientific, commercial). Each involves the labeling of complex, multi-word spans that pick out different healthcare concepts. We also introduce a new labeled dataset for identifying the treatment relations between drugs and diseases. |
| Tasks | |
| Published | 2018-10-31 |
| URL | http://arxiv.org/abs/1811.00070v2 |
| http://arxiv.org/pdf/1811.00070v2.pdf | |
| PWC | https://paperswithcode.com/paper/effective-feature-representation-for-clinical |
| Repo | |
| Framework | |
Visualizing Convolutional Neural Networks to Improve Decision Support for Skin Lesion Classification
| Title | Visualizing Convolutional Neural Networks to Improve Decision Support for Skin Lesion Classification |
| Authors | Pieter Van Molle, Miguel De Strooper, Tim Verbelen, Bert Vankeirsbilck, Pieter Simoens, Bart Dhoedt |
| Abstract | Because of their state-of-the-art performance in computer vision, CNNs are becoming increasingly popular in a variety of fields, including medicine. However, as neural networks are black box function approximators, it is difficult, if not impossible, for a medical expert to reason about their output. This could potentially result in the expert distrusting the network when he or she does not agree with its output. In such a case, explaining why the CNN makes a certain decision becomes valuable information. In this paper, we try to open the black box of the CNN by inspecting and visualizing the learned feature maps, in the field of dermatology. We show that, to some extent, CNNs focus on features similar to those used by dermatologists to make a diagnosis. However, more research is required for fully explaining their output. |
| Tasks | Skin Lesion Classification |
| Published | 2018-09-11 |
| URL | http://arxiv.org/abs/1809.03851v1 |
| http://arxiv.org/pdf/1809.03851v1.pdf | |
| PWC | https://paperswithcode.com/paper/visualizing-convolutional-neural-networks-to |
| Repo | |
| Framework | |
Skill Rating for Generative Models
| Title | Skill Rating for Generative Models |
| Authors | Catherine Olsson, Surya Bhupatiraju, Tom Brown, Augustus Odena, Ian Goodfellow |
| Abstract | We explore a new way to evaluate generative models using insights from evaluation of competitive games between human players. We show experimentally that tournaments between generators and discriminators provide an effective way to evaluate generative models. We introduce two methods for summarizing tournament outcomes: tournament win rate and skill rating. Evaluations are useful in different contexts, including monitoring the progress of a single model as it learns during the training process, and comparing the capabilities of two different fully trained models. We show that a tournament consisting of a single model playing against past and future versions of itself produces a useful measure of training progress. A tournament containing multiple separate models (using different seeds, hyperparameters, and architectures) provides a useful relative comparison between different trained GANs. Tournament-based rating methods are conceptually distinct from numerous previous categories of approaches to evaluation of generative models, and have complementary advantages and disadvantages. |
| Tasks | |
| Published | 2018-08-14 |
| URL | http://arxiv.org/abs/1808.04888v1 |
| http://arxiv.org/pdf/1808.04888v1.pdf | |
| PWC | https://paperswithcode.com/paper/skill-rating-for-generative-models |
| Repo | |
| Framework | |
VisualBackProp for learning using privileged information with CNNs
| Title | VisualBackProp for learning using privileged information with CNNs |
| Authors | Devansh Bisla, Anna Choromanska |
| Abstract | In many machine learning applications, from medical diagnostics to autonomous driving, the availability of prior knowledge can be used to improve the predictive performance of learning algorithms and incorporate physical,' domain knowledge,’ or `common sense’ concepts into training of machine learning systems as well as verify constraints/properties of the systems. We explore the learning using privileged information paradigm and show how to incorporate the privileged information, such as segmentation mask available along with the classification label of each example, into the training stage of convolutional neural networks. This is done by augmenting the CNN model with an architectural component that effectively focuses model’s attention on the desired region of the input image during the training process and that is transparent to the network’s label prediction mechanism at testing. This component effectively corresponds to the visualization strategy for identifying the parts of the input, often referred to as visualization mask, that most contribute to the prediction, yet uses this strategy in reverse to the classical setting in order to enforce the desired visualization mask instead. We verify our proposed algorithms through exhaustive experiments on benchmark ImageNet and PASCAL VOC data sets and achieve improvements in the performance of $2.4%$ and $2.7%$ over standard single-supervision model training. Finally, we confirm the effectiveness of our approach on skin lesion classification problem. | |
| Tasks | Autonomous Driving, Common Sense Reasoning, Skin Lesion Classification |
| Published | 2018-05-24 |
| URL | http://arxiv.org/abs/1805.09474v1 |
| http://arxiv.org/pdf/1805.09474v1.pdf | |
| PWC | https://paperswithcode.com/paper/visualbackprop-for-learning-using-privileged |
| Repo | |
| Framework | |
SDFN: Segmentation-based Deep Fusion Network for Thoracic Disease Classification in Chest X-ray Images
| Title | SDFN: Segmentation-based Deep Fusion Network for Thoracic Disease Classification in Chest X-ray Images |
| Authors | Han Liu, Lei Wang, Yandong Nan, Faguang Jin, Jiantao Pu |
| Abstract | This study aims to automatically diagnose thoracic diseases depicted on the chest x-ray (CXR) images using deep convolutional neural networks. The existing methods generally used the entire CXR images for training purposes, but this strategy may suffer from two drawbacks. First, potential misalignment or the existence of irrelevant objects in the entire CXR images may cause unnecessary noise and thus limit the network performance. Second, the relatively low image resolution caused by the resizing operation, which is a common preprocessing procedure for training neural networks, may lead to the loss of image details, making it difficult to detect pathologies with small lesion regions. To address these issues, we present a novel method termed as segmentation-based deep fusion network (SDFN), which leverages the higher-resolution information of local lung regions. Specifically, the local lung regions were identified and cropped by the Lung Region Generator (LRG). Two CNN-based classification models were then used as feature extractors to obtain the discriminative features of the entire CXR images and the cropped lung region images. Lastly, the obtained features were fused by the feature fusion module for disease classification. Evaluated by the NIH benchmark split on the Chest X-ray 14 Dataset, our experimental result demonstrated that the developed method achieved more accurate disease classification compared with the available approaches via the receiver operating characteristic (ROC) analyses. It was also found that the SDFN could localize the lesion regions more precisely as compared to the traditional method. |
| Tasks | Thoracic Disease Classification |
| Published | 2018-10-30 |
| URL | http://arxiv.org/abs/1810.12959v1 |
| http://arxiv.org/pdf/1810.12959v1.pdf | |
| PWC | https://paperswithcode.com/paper/sdfn-segmentation-based-deep-fusion-network |
| Repo | |
| Framework | |
Image Segmentation with Pseudo-marginal MCMC Sampling and Nonparametric Shape Priors
| Title | Image Segmentation with Pseudo-marginal MCMC Sampling and Nonparametric Shape Priors |
| Authors | Ertunc Erdil, Sinan Yildirim, Tolga Tasdizen, Mujdat Cetin |
| Abstract | In this paper, we propose an efficient pseudo-marginal Markov chain Monte Carlo (MCMC) sampling approach to draw samples from posterior shape distributions for image segmentation. The computation time of the proposed approach is independent from the size of the training set used to learn the shape prior distribution nonparametrically. Therefore, it scales well for very large data sets. Our approach is able to characterize the posterior probability density in the space of shapes through its samples, and to return multiple solutions, potentially from different modes of a multimodal probability density, which would be encountered, e.g., in segmenting objects from multiple shape classes. Experimental results demonstrate the potential of the proposed approach. |
| Tasks | Semantic Segmentation |
| Published | 2018-09-03 |
| URL | http://arxiv.org/abs/1809.00488v1 |
| http://arxiv.org/pdf/1809.00488v1.pdf | |
| PWC | https://paperswithcode.com/paper/image-segmentation-with-pseudo-marginal-mcmc |
| Repo | |
| Framework | |
Multi-View Semantic Labeling of 3D Point Clouds for Automated Plant Phenotyping
| Title | Multi-View Semantic Labeling of 3D Point Clouds for Automated Plant Phenotyping |
| Authors | Bernhard Japes, Jennifer Mack, Florian Rist, Katja Herzog, Reinhard Töpfer, Volker Steinhage |
| Abstract | Semantic labeling of 3D point clouds is important for the derivation of 3D models from real world scenarios in several economic fields such as building industry, facility management, town planning or heritage conservation. In contrast to these most common applications, we describe in this study the semantic labeling of 3D point clouds derived from plant organs by high-precision scanning. Our approach is optimized for the task of plant phenotyping with its very specific challenges and is employing a deep learning framework. Thereby, we report important experiences concerning detailed parameter initialization and optimization techniques. By evaluating our approach with challenging datasets we achieve state-of-the-art results without difficult and time consuming feature engineering as being necessary in traditional approaches to semantic labeling. |
| Tasks | Feature Engineering |
| Published | 2018-05-10 |
| URL | http://arxiv.org/abs/1805.03994v2 |
| http://arxiv.org/pdf/1805.03994v2.pdf | |
| PWC | https://paperswithcode.com/paper/multi-view-semantic-labeling-of-3d-point |
| Repo | |
| Framework | |
Fingerprint Distortion Rectification using Deep Convolutional Neural Networks
| Title | Fingerprint Distortion Rectification using Deep Convolutional Neural Networks |
| Authors | Ali Dabouei, Hadi Kazemi, Seyed Mehdi Iranmanesh, Jeremi Dawson, Nasser M. Nasrabadi |
| Abstract | Elastic distortion of fingerprints has a negative effect on the performance of fingerprint recognition systems. This negative effect brings inconvenience to users in authentication applications. However, in the negative recognition scenario where users may intentionally distort their fingerprints, this can be a serious problem since distortion will prevent recognition system from identifying malicious users. Current methods aimed at addressing this problem still have limitations. They are often not accurate because they estimate distortion parameters based on the ridge frequency map and orientation map of input samples, which are not reliable due to distortion. Secondly, they are not efficient and requiring significant computation time to rectify samples. In this paper, we develop a rectification model based on a Deep Convolutional Neural Network (DCNN) to accurately estimate distortion parameters from the input image. Using a comprehensive database of synthetic distorted samples, the DCNN learns to accurately estimate distortion bases ten times faster than the dictionary search methods used in the previous approaches. Evaluating the proposed method on public databases of distorted samples shows that it can significantly improve the matching performance of distorted samples. |
| Tasks | |
| Published | 2018-01-03 |
| URL | http://arxiv.org/abs/1801.01198v1 |
| http://arxiv.org/pdf/1801.01198v1.pdf | |
| PWC | https://paperswithcode.com/paper/fingerprint-distortion-rectification-using |
| Repo | |
| Framework | |
Scope of Research on Particle Swarm Optimization Based Data Clustering
| Title | Scope of Research on Particle Swarm Optimization Based Data Clustering |
| Authors | Vishakha A Metre, Mr Pramod B Deshmukh |
| Abstract | Optimization is nothing but a mathematical technique which finds maxima or minima of any function of concern in some realistic region. Different optimization techniques are proposed which are competing for the best solution. Particle Swarm Optimization (PSO) is a new, advanced, and most powerful optimization methodology that performs empirically well on several optimization problems. It is the extensively used Swarm Intelligence (SI) inspired optimization algorithm used for finding the global optimal solution in a multifaceted search region. Data clustering is one of the challenging real world applications that invite the eminent research works in variety of fields. Applicability of different PSO variants to data clustering is studied in the literature, and the analyzed research work shows that, PSO variants give poor results for multidimensional data. This paper describes the different challenges associated with multidimensional data clustering and scope of research on optimizing the clustering problems using PSO. We also propose a strategy to use hybrid PSO variant for clustering multidimensional numerical, text and image data. |
| Tasks | |
| Published | 2018-12-06 |
| URL | http://arxiv.org/abs/1903.12073v1 |
| http://arxiv.org/pdf/1903.12073v1.pdf | |
| PWC | https://paperswithcode.com/paper/scope-of-research-on-particle-swarm |
| Repo | |
| Framework | |
