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.

Digital cameras have become almost ubiquitous and their use for fast and casual capturing of natural images is unchallenged. For making images of documents, however, they have not caught up to flatbed scanners yet, mainly because camera images tend to suffer from distortion due to the perspective and are therefore limited in their further use for archival or OCR. For images of non-planar paper surfaces like books, page curl causes additional distortion, which poses an even greater problem due to its nonlinearity. This paper presents a new algorithm for removing both perspective and page curl distortion. It requires only a single camera image as input and relies on a priori layout information instead of additional hardware. Therefore, it is much more user friendly than most previous approaches, and allows for flexible ad hoc document capture. Results are presented showing that the algorithm produces visually pleasing output and increases OCR accuracy, thus having the potential to become a general purpose preprocessing tool for camera based document capture.

/pdf/document-image-dewarping-using-robust-estimation-of-curled-335f5rgb02.pdf

Document image dewarping using robust estimation of curled text lines

Grouping and recognition are important components of visual scene understanding, e.g., for object detection and semantic segmentation. With end-to-end deep learning systems, grouping of image regions usually happens implicitly via top-down supervision from pixel-level recognition labels. Instead, in this paper, we propose to bring back the grouping mechanism into deep networks, which allows semantic segments to emerge automatically with only text supervision. We propose a hierarchical Grouping Vision Transformer (GroupViT), which goes beyond the regular grid structure representation and learns to group image regions into progressively larger arbitrary-shaped segments. We train GroupViT jointly with a text encoder on a large-scale image-text dataset via contrastive losses. With only text supervision and without any pixel-level annotations, GroupViT learns to group together semantic regions and successfully transfers to the task of semantic segmentation in a zero-shot manner, i.e., without any further fine-tuning. It achieves a zero-shot accuracy of 52.3% mIoU on the PASCAL VOC 2012 and 22.4% mIoU on PASCAL Context datasets, and performs competitively to state-of-the-art transfer-learning methods requiring greater levels of supervision. We open-source our code at https://github.com/NVlabs/GroupViT.

GroupViT: Semantic Segmentation Emerges from Text Supervision

In this paper, I summarize research in document layout analysis carried out over the last few years in our laboratory. Correct document layout analysis is a key step in document capture conversions into electronic formats, optical character recognition (OCR), information retrieval from scanned documents, appearance-based document retrieval, and reformatting of documents for on-screen display. We have developed a number of novel geometric algorithms and statistical methods. Layout analysis systems built from these algorithms are applicable to a wide variety of languages and layouts, and have proven to be robust to the presence of noise and spurious features in a page image. The system itself consists of reusable and independent software modules that can be reconfigured to be adapted to different languages and applications. Currently, we are using them for electronic book and document capture applications. If there is commercial or government demand, we are interested in adapting these tools to information retrieval and intelligence applications.

/pdf/high-performance-document-layout-analysis-1up7t6rvo1.pdf

High Performance Document Layout Analysis

Recurrent neural networks (RNN) have been successfully applied for recognition of cursive handwritten documents, both in English and Arabic scripts. Ability of RNNs to model context in sequence data like speech and text makes them a suitable candidate to develop OCR systems for printed Nabataean scripts (including Nastaleeq for which no OCR system is available to date). In this work, we have presented the results of applying RNN to printed Urdu text in Nastaleeq script. Bidirectional Long Short Term Memory (BLSTM) architecture with Connectionist Temporal Classification (CTC) output layer was employed to recognize printed Urdu text. We evaluated BLSTM networks for two cases: one ignoring the character's shape variations and the second is considering them. The recognition error rate at character level for first case is 5.15% and for the second is 13.6%. These results were obtained on synthetically generated UPTI dataset containing artificially degraded images to reflect some real-world scanning artifacts along with clean images. Comparison with shape-matching based method is also presented.

Offline Printed Urdu Nastaleeq Script Recognition with Bidirectional LSTM Networks

https://www.dfki.de/web/forschung/publikationen/renameFileForDownload?file_id=uploads_549&filename=ImplementationBranchBound.pdf

Thomas M. Breuel

Papers

Document image dewarping using robust estimation of curled text lines

GroupViT: Semantic Segmentation Emerges from Text Supervision

High Performance Document Layout Analysis

Offline Printed Urdu Nastaleeq Script Recognition with Bidirectional LSTM Networks

Implementation techniques for geometric branch-and-bound matching methods