https://www2.econ.iastate.edu/tesfatsi/DeepLearningInNeuralNetworksOverview.JSchmidhuber2015.pdf

Deep learning in neural networks

In this work we address the task of semantic image segmentation with Deep Learning and make three main contributions that are experimentally shown to have substantial practical merit. First , we highlight convolution with upsampled filters, or ‘atrous convolution’, as a powerful tool in dense prediction tasks. Atrous convolution allows us to explicitly control the resolution at which feature responses are computed within Deep Convolutional Neural Networks. It also allows us to effectively enlarge the field of view of filters to incorporate larger context without increasing the number of parameters or the amount of computation. Second , we propose atrous spatial pyramid pooling (ASPP) to robustly segment objects at multiple scales. ASPP probes an incoming convolutional feature layer with filters at multiple sampling rates and effective fields-of-views, thus capturing objects as well as image context at multiple scales. Third , we improve the localization of object boundaries by combining methods from DCNNs and probabilistic graphical models. The commonly deployed combination of max-pooling and downsampling in DCNNs achieves invariance but has a toll on localization accuracy. We overcome this by combining the responses at the final DCNN layer with a fully connected Conditional Random Field (CRF), which is shown both qualitatively and quantitatively to improve localization performance. Our proposed “DeepLab” system sets the new state-of-art at the PASCAL VOC-2012 semantic image segmentation task, reaching 79.7 percent mIOU in the test set, and advances the results on three other datasets: PASCAL-Context, PASCAL-Person-Part, and Cityscapes. All of our code is made publicly available online.

DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs

Image-to-image translation is a class of vision and graphics problems where the goal is to learn the mapping between an input image and an output image using a training set of aligned image pairs. However, for many tasks, paired training data will not be available. We present an approach for learning to translate an image from a source domain X to a target domain Y in the absence of paired examples. Our goal is to learn a mapping G : X → Y such that the distribution of images from G(X) is indistinguishable from the distribution Y using an adversarial loss. Because this mapping is highly under-constrained, we couple it with an inverse mapping F : Y → X and introduce a cycle consistency loss to push F(G(X)) ≈ X (and vice versa). Qualitative results are presented on several tasks where paired training data does not exist, including collection style transfer, object transfiguration, season transfer, photo enhancement, etc. Quantitative comparisons against several prior methods demonstrate the superiority of our approach.

Unpaired Image-to-Image Translation Using Cycle-Consistent Adversarial Networks

Probability Distributions.- Linear Models for Regression.- Linear Models for Classification.- Neural Networks.- Kernel Methods.- Sparse Kernel Machines.- Graphical Models.- Mixture Models and EM.- Approximate Inference.- Sampling Methods.- Continuous Latent Variables.- Sequential Data.- Combining Models.

Pattern Recognition and Machine Learning

In this work we address the task of semantic image segmentation with Deep Learning and make three main contributions that are experimentally shown to have substantial practical merit. First, we highlight convolution with upsampled filters, or 'atrous convolution', as a powerful tool in dense prediction tasks. Atrous convolution allows us to explicitly control the resolution at which feature responses are computed within Deep Convolutional Neural Networks. It also allows us to effectively enlarge the field of view of filters to incorporate larger context without increasing the number of parameters or the amount of computation. Second, we propose atrous spatial pyramid pooling (ASPP) to robustly segment objects at multiple scales. ASPP probes an incoming convolutional feature layer with filters at multiple sampling rates and effective fields-of-views, thus capturing objects as well as image context at multiple scales. Third, we improve the localization of object boundaries by combining methods from DCNNs and probabilistic graphical models. The commonly deployed combination of max-pooling and downsampling in DCNNs achieves invariance but has a toll on localization accuracy. We overcome this by combining the responses at the final DCNN layer with a fully connected Conditional Random Field (CRF), which is shown both qualitatively and quantitatively to improve localization performance. Our proposed "DeepLab" system sets the new state-of-art at the PASCAL VOC-2012 semantic image segmentation task, reaching 79.7% mIOU in the test set, and advances the results on three other datasets: PASCAL-Context, PASCAL-Person-Part, and Cityscapes. All of our code is made publicly available online.

Source IP addresses are often used as a major feature for user modeling in computer networks. Particularly in the field of Distributed Denial of Service (DDoS) attack detection and mitigation traffic models make extensive use of source IP addresses for detecting anomalies. Typically the real IP address distribution is strongly undersampled due to a small amount of observations. Density estimation overcomes this shortage by taking advantage of IP neighborhood relations. In many cases simple models are implicitly used or chosen intuitively as a network based heuristic. In this paper we review and formalize existing models including a hierarchical clustering approach first. In addition, we present a modified k-means clustering algorithm for source IP density estimation as well as a statistical motivated smoothing approach using the Nadaraya-Watson kernel-weighted average. For performance evaluation we apply all methods on a 90 days real world dataset consisting of 1.3 million different source IP addresses and try to predict the users of the following next 10 days. ROC curves and an example DDoS mitigation scenario show that there is no uniformly better approach: k-means performs best when a high detection rate is needed whereas statistical smoothing works better for low false alarm rate requirements like the DDoS mitigation scenario.

/pdf/server-side-prediction-of-source-ip-addresses-using-density-11pxv4cczt.pdf

Server-Side Prediction of Source IP Addresses Using Density Estimation

Document images prove to be a difficult case for standard stereo correspondence approaches. One of the major problem is that document images are highly self-similar. Most algorithms try to tackle this problem by incorporating a global optimization scheme, which tends to be computationally expensive. In this paper, we show that incorporation of layout information into the matching paradigm, as a grouping entity for features, leads to better results in terms of robustness, efficiency, and ultimately in a better 3D model of the captured document, that can be used in various document restoration systems. This can be seen as a divide and conquer approach that partitions the search space into portions given by each grouping entity and then solves each of them independently. As a grouping entity text-lines are preferred over individual character blobs because it is easier to establish correspondences. Text-line extraction works reasonably well on stereo image pairs in the presence of perspective distortions. The proposed approach is highly efficient and matches obtained are more reliable. The claims are backed up by showing their practical applicability through experimental evaluations.

https://www.dfki.de/web/forschung/publikationen/renameFileForDownload?filename=Zeeshan-Stereo-Matching-DAS12.pdf&file_id=uploads_1262

Improvements to Uncalibrated Feature-Based Stereo Matching for Document Images by Using Text-Line Segmentation

This paper presents the current status of Decapod's English font reconstruction. The Potrace algorithm and its parameters that affect glyph shape are examined. The visual fidelity of Decapod's font reconstruction is shown and compared to Adobe ClearScanTM. The font reconstruction details of the two methods are presented. The experiment demonstrates the capabilities of the two methods in reconstructing the font for a synthetic book typeset each time with one of six English fonts, three serif and three sans-serif. For both typefaces, Decapod is able to create a reusable TTF font that is embedded in the generated PDF document.

On the performance of Decapod's digital font reconstruction

The character recognition of cursive scripts always be provocative. The inherent challenges exists in cursive scripts captured researcher’s interest to crop up the issues that surface in building a reliable OCR. There exists many ancient languages that require state of the art techniques to be applied on them. Every such language has its own inherent complex structure. We proposed Balinese character recognition system by Recurrent Neural Network (RNN) approach, so that their characteristics may get substantial attention from research community. The Balinese has Brahmic Indic ancestor having cursive writing style nearest to Devangri, Sinhala and Tamil. We employed BLSTM networks on Balinese character recognition.

Balinese Character Recognition Using Bidirectional LSTM Classifier

The aim of this work is to investigate Long Short-Term Memory (LSTM) for finding the semantic associations between two parallel text lines of different instances of the same class sequence. In this work, we propose a new model called class-less classifier, which is cognitive motivated by a simplified version of the infants learning. The presented model not only learns the semantic association but also learns the relation between the labels and the classes. In addition, our model uses two parallel class-less LSTM networks and the learning rule is based on the alignment of both networks. For testing purposes, a parallel sequence dataset is generated based on MNIST dataset, which is a standard dataset for handwritten digit recognition. The results of our model were similar to the standard LSTM.

Thomas M. Breuel

Papers

Server-Side Prediction of Source IP Addresses Using Density Estimation

Improvements to Uncalibrated Feature-Based Stereo Matching for Document Images by Using Text-Line Segmentation

On the performance of Decapod's digital font reconstruction

Balinese Character Recognition Using Bidirectional LSTM Classifier

Parallel sequence classification using recurrent neural networks and alignment