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.

Automatic image tagging is becoming increasingly important to organize large amounts of image data. To identify concepts in images, these tagging systems rely on large sets of annotated image training sets. In this work we analyze image sets taken from online community-driven image databases, such as Flickr, for use in concept identification. Real-world performance is measured using our flexible tagging system, Tagr.

https://www.dfki.de/web/forschung/publikationen/renameFileForDownload?filename=2008-IUPR-18Aug_0756.pdf&file_id=uploads_382

Automatic image tagging using community-driven online image databases

Atomic segmentation of cursive scripts into constituent characters is one of the most challenging problems in pattern recognition. To avoid segmentation in cursive script, concrete shapes are considered as recognizable units. Therefore, the objective of this work is to find out the alternate recognizable units in Pashto cursive script. These alternatives are ligatures and primary ligatures. However, we need sound statistical analysis to find the appropriate numbers of ligatures and primary ligatures in Pashto script. In this work, a corpus of 2, 313, 736 Pashto words are extracted from a large scale diversified web sources, and total of 19, 268 unique ligatures have been identified in Pashto cursive script. Analysis shows that only 7000 ligatures represent 91% portion of overall corpus of the Pashto unique words. Similarly, about 7, 681 primary ligatures are also identified which represent the basic shapes of all the ligatures.

Recognizable units in Pashto language for OCR

Symbol recognition is important in many applications such as the automated interpretation of line drawings and retrieval-by-content search engines. This paper presents the use of geometric matching for symbol recognition under similarity transformations. We incorporate this matching approach in a complete symbol recognition/spotting system, which consists of denoising, symbol representation and recognition. The proposed system works for both isolated recognition and spotting symbols in context. For denoising, we use an adaptive preprocessing algorithm. For symbol representation, pixels and/or vectorial primitives can be used, then the recognition is done via geometric matching. When applied on the datasets of GREC'05 and GREC'11 symbol recognition contests, the system has performed significantly better than other statistical or structural methods.

On the use of geometric matching for both: isolated symbol recognition and symbol spotting

In this work, we describe the use of statistical grouping for partitioning line drawings into shapes, those shapes represent meaningful parts of the symbols that constitute the line drawings. This grouping method converts a complete line drawing into a set of isolated shapes. This conversion has two effects: (1) making isolated recognition methods applicable for spotting symbols in context, (2) identifying potential regions of interest for symbol spotting methods, hence making them perform faster and more accurately. Our grouping is based on finding salient convex groups of geometric primitives, followed by combining certain found convex groups together. Additionally, we show how such grouping can be used for symbol spotting. When applied on a dataset of architectural line drawings the grouping method achieved above 98.8% recall and 97.3% precision for finding symbols parts. Using the grouping information, the spotting method achieved 99.3% recall and 99.9% precision. Compared to the performance of the same method without grouping information, an overall speed-up factor of 3.2 is achieved with the same -- or better -- recall and precision values.

Statistical Grouping for Segmenting Symbols Parts from Line Drawings, with Application to Symbol Spotting

Identifying the underlying directional relations from observational time series with nonlinear interactions and complex relational structures is key to a wide range of applications, yet remains a hard problem. In this work, we introduce a novel minimum predictive information regularization method to infer directional relations from time series, allowing deep learning models to discover nonlinear relations. Our method substantially outperforms other methods for learning nonlinear relations in synthetic datasets, and discovers the directional relations in a video game environment and a heart-rate vs. breath-rate dataset.

Thomas M. Breuel

Papers

Automatic image tagging using community-driven online image databases

Recognizable units in Pashto language for OCR

On the use of geometric matching for both: isolated symbol recognition and symbol spotting

Statistical Grouping for Segmenting Symbols Parts from Line Drawings, with Application to Symbol Spotting

Discovering Nonlinear Relations with Minimum Predictive Information Regularization.