This research is the second phase in a series of investigations on developing an Optical Character Recognition (OCR) of Arabic historical documents and examining how different modeling procedures interact with the problem. The first research studied the effect of Transformers on our custom-built Arabic dataset. One of the downsides of the first research was the size of the training data, a mere 15000 images from our 30 million images, due to lack of resources. Also, we add an image enhancement layer, time and space optimization, and Post-Correction layer to aid the model in predicting the correct word for the correct context. Notably, we propose an end-to-end text recognition approach using Vision Transformers as an encoder, namely BEIT, and vanilla Transformer as a decoder, eliminating CNNs for feature extraction and reducing the model's complexity. The experiments show that our end-to-end model outperforms Convolutions Backbones. The model attained a CER of 4.46%.

--Network alignment task, which aims to identify corresponding nodes in different networks, is of great significance for many subsequent applications. Without the need for labeled anchor links, unsupervised alignment methods have been attracting more and more attention. However, the topological consistency assumptions defined by existing methods are generally low-order and less accurate because only the edge-indiscriminative topological pattern is considered, which is especially risky in an unsupervised setting. T o reposition the focus of the alignment process from low-order to higher-order topological consistency, in this paper, we propose a fully unsupervised network alignment framework named HTC. The proposed higher-order topological consistency is formulated based on edge orbits, which is merged into the information aggregation process of a graph convolutional network so that the alignment consistencies are transformed into the similarity of node embeddings. Furthermore, the encoder is trained to be multi-orbit-aware and then be refined to identify more trusted anchor links. Node correspondence is comprehensively evaluated by integrating all different orders of consistency. In addition to sound theoretical analysis, the superiority of the proposed method is also empirically demonstrated through extensive experimental evaluation. On three pairs of real-world datasets and two pairs of synthetic datasets, our HTC consistently outperforms a wide variety of unsupervised and supervised methods with the least or comparable time consumption. It also exhibits robustness to structural noise as a result of our multi-orbit-aware training mechanism. Network alignment task, which aims to identify entity correspondence across different networks, is usually the very first step of many downstream analyzing tasks. For instance, recognizing the same user on different social networks can facilitate friend suggestion, item recommendation, personalized advertisement [1]-[5]. Similar scenarios also exist widely in other fields, such as protein network analysis [6], knowledge discovery [7], etc. Identifying corresponding nodes across different networks is an extremely hard task, even for humans. Manually labelling correspondence can be prohibitively challenging, expensive (in human efforts, time, and money costs), and tedious [8]. Due to such obstacles, in some cases, it may be impractical to get access to sufficient labels for training well-performed supervised or even semi-supervised models [4], [9]. By contrast, unsupervised models can be trained without the need for labeled data, which is more flexible and practical in real-world application scenarios. Thus, unsupervised alignment methods have been drawing a surge of interest recently [10]-[12].

Non-convex multidimensional optimization and the related problem of finding the global minimum in rough landscapes are crucial challenges of modern science. Such problems were extensively studied in the context of the spin-glass systems [1], and found applications in biology [2], finance [3], and data science [4]. Here, we focus on a task motivated by data science and consider the model of the signal recovering from a noisy high-dimensional data tensor - the spiked tensor model (tensor PCA) [5, 6, 7].

Many automatic speech recognition (ASR) data sets include a single pre-defined test set consisting of one or more speakers whose speech never appears in the training set. This "hold-speaker(s)-out" data partitioning strategy, however, may not be ideal for data sets in which the number of speakers is very small. This study investigates ten different data split methods for five languages with minimal ASR training resources. We find that (1) model performance varies greatly depending on which speaker is selected for testing; (2) the average word error rate (WER) across all held-out speakers is comparable not only to the average WER over multiple random splits but also to any given individual random split; (3) WER is also generally comparable when the data is split heuristically or adversarially; (4) utterance duration and intensity are comparatively more predictive factors of variability regardless of the data split. These results suggest that the widely used hold-speakers-out approach to ASR data partitioning can yield results that do not reflect model performance on unseen data or speakers. Random splits can yield more reliable and generalizable estimates when facing data sparsity.

In this paper we introduce the FooDI-ML dataset. This dataset contains over 1.5M unique images and over 9.5M store names, product names descriptions, and collection sections gathered from the Glovo application. The data made available corresponds to food, drinks and groceries products from 37 countries in Europe, the Middle East, Africa and Latin America. The dataset comprehends 33 languages, including 870K samples of languages of countries from Eastern Europe and Western Asia such as Ukrainian and Kazakh, which have been so far underrepresented in publicly available visio-linguistic datasets. The dataset also includes widely spoken languages such as Spanish and English. To assist further research, we include benchmarks over two tasks: text-image retrieval and conditional image generation.

Deep Learning Indaba is currently taking place in Tunis, Tunisia. Find out what the participants and organisers have been up to in this round-up of tweets from attendees. This has me really thinking about how humans do this so seamlessly and the effort required from a deep learning perspective. Gabriela Csurka is delivering a powerful keynote speech on "Visual Domain Adaptation in the Deep Learning Era" at the @DeepIndaba #DLIndaba2022. Follow us to get the most recent updates of the #DLIndaba2022.

Multiresolution deep learning approaches, such as the U-Net architecture, have achieved high performance in classifying and segmenting images. However, these approaches do not provide a latent image representation and cannot be used to decompose, denoise, and reconstruct image data. The U-Net and other convolutional neural network (CNNs) architectures commonly use pooling to enlarge the receptive field, which usually results in irreversible information loss. This study proposes to include a Riesz-Quincunx (RQ) wavelet transform, which combines 1) higher-order Riesz wavelet transform and 2) orthogonal Quincunx wavelets (which have both been used to reduce blur in medical images) inside the U-net architecture, to reduce noise in satellite images and their time-series. In the transformed feature space, we propose a variational approach to understand how random perturbations of the features affect the image to further reduce noise. Combining both approaches, we introduce a hybrid RQUNet-VAE scheme for image and time series decomposition used to reduce noise in satellite imagery. We present qualitative and quantitative experimental results that demonstrate that our proposed RQUNet-VAE was more effective at reducing noise in satellite imagery compared to other state-of-the-art methods. We also apply our scheme to several applications for multi-band satellite images, including: image denoising, image and time-series decomposition by diffusion and image segmentation.

Federated learning (FL) aims to learn joint knowledge from a large scale of decentralized devices with labeled data in a privacy-preserving manner. However, since high-quality labeled data require expensive human intelligence and efforts, data with incorrect labels (called noisy labels) are ubiquitous in reality, which inevitably cause performance degradation. Although a lot of methods are proposed to directly deal with noisy labels, these methods either require excessive computation overhead or violate the privacy protection principle of FL. To this end, we focus on this issue in FL with the purpose of alleviating performance degradation yielded by noisy labels meanwhile guaranteeing data privacy. Specifically, we propose a Local Self-Regularization method, which effectively regularizes the local training process via implicitly hindering the model from memorizing noisy labels and explicitly narrowing the model output discrepancy between original and augmented instances using self distillation. Experimental results demonstrate that our proposed method can achieve notable resistance against noisy labels in various noise levels on three benchmark datasets. In addition, we integrate our method with existing state-of-the-arts and achieve superior performance on the real-world dataset Clothing1M. The code is available at https://github.com/Sprinter1999/FedLSR.

Currency is used almost everywhere to facilitate business. In most developing countries, especially the ones in Africa, tangible notes are predominantly used in everyday financial transactions. One of these countries, Ethiopia, is believed to have one of the world highest rates of blindness (1.6%) and low vision (3.7%). There are around 4 million visually impaired people; With 1.7 million people being in complete vision loss. Those people face a number of challenges when they are in a bus station, in shopping centers, or anywhere which requires the physical exchange of money. In this paper, we try to provide a solution to this issue using AI/ML applications. We developed an Android and IOS compatible mobile application with a model that achieved 98.9% classification accuracy on our dataset. The application has a voice integrated feature that tells the type of the scanned currency in Amharic, the working language of Ethiopia. The application is developed to be easily accessible by its users. It is build to reduce the burden of visually impaired people in Ethiopia.

Developing innovative informatics approaches aimed to enhance fetal monitoring is a burgeoning field of study in reproductive medicine. Several reviews have been conducted regarding Artificial intelligence (AI) techniques to improve pregnancy outcomes. They are limited by focusing on specific data such as mother's care during pregnancy. This systematic survey aims to explore how artificial intelligence (AI) can assist with fetal growth monitoring via Ultrasound (US) image. We used eight medical and computer science bibliographic databases, including PubMed, Embase, PsycINFO, ScienceDirect, IEEE explore, ACM Library, Google Scholar, and the Web of Science. We retrieved studies published between 2010 to 2021. Data extracted from studies were synthesized using a narrative approach. Out of 1269 retrieved studies, we included 107 distinct studies from queries that were relevant to the topic in the survey. We found that 2D ultrasound images were more popular (n=88) than 3D and 4D ultrasound images (n=19). Classification is the most used method (n=42), followed by segmentation (n=31), classification integrated with segmentation (n=16) and other miscellaneous such as object-detection, regression and reinforcement learning (n=18). The most common areas within the pregnancy domain were the fetus head (n=43), then fetus body (n=31), fetus heart (n=13), fetus abdomen (n=10), and lastly the fetus face (n=10). In the most recent studies, deep learning techniques were primarily used (n=81), followed by machine learning (n=16), artificial neural network (n=7), and reinforcement learning (n=2). AI techniques played a crucial role in predicting fetal diseases and identifying fetus anatomy structures during pregnancy. More research is required to validate this technology from a physician's perspective, such as pilot studies and randomized controlled trials on AI and its applications in a hospital setting.