Related papers: The Notary in the Haystack -- Countering Class Imb…
Most of the textual information available to us are temporally variable. In a world where information is dynamic, time-stamping them is a very important task. Documents are a good source of information and are used for many tasks like,…
Segmentation is a fundamental task in medical image analysis. The clinical interest is often to measure the volume of a structure. To evaluate and compare segmentation methods, the similarity between a segmentation and a predefined ground…
Deep convolutional neural networks (CNNs) have been intensively used for multi-class segmentation of data from different modalities and achieved state-of-the-art performances. However, a common problem when dealing with large, high…
Neural Networks are prone to having lesser accuracy in the classification of images with noise perturbation. Convolutional Neural Networks, CNNs are known for their unparalleled accuracy in the classification of benign images. But our study…
In this paper, we investigate the use of Convolutional Neural Networks for counting the number of records in historical handwritten documents. With this work we demonstrate that training the networks only with synthetic images allows us to…
While machine learning (ML) architectures have evolved rapidly to account for complex data, loss functions like cross-entropy remain mostly structure-agnostic in many real-world applications. However, the `class-symmetric' nature of these…
Text segmentation is important for signaling a document's structure. Without segmenting a long document into topically coherent sections, it is difficult for readers to comprehend the text, let alone find important information. The problem…
Falsely annotated samples, also known as noisy labels, can significantly harm the performance of deep learning models. Two main approaches for learning with noisy labels are global noise estimation and data filtering. Global noise…
High-quality pixel-level annotations are essential for the semantic segmentation of remote sensing imagery. However, such labels are expensive to obtain and often affected by noise due to the labor-intensive and time-consuming nature of…
Text Categorization (TC), also known as Text Classification, is the task of automatically classifying a set of text documents into different categories from a predefined set. If a document belongs to exactly one of the categories, it is a…
Binarization of digital documents is the task of classifying each pixel in an image of the document as belonging to the background (parchment/paper) or foreground (text/ink). Historical documents are often subjected to degradations, that…
Several image processing tasks, such as image classification and object detection, have been significantly improved using Convolutional Neural Networks (CNN). Like ResNet and EfficientNet, many architectures have achieved outstanding…
We introduce DocSCAN, a completely unsupervised text classification approach using Semantic Clustering by Adopting Nearest-Neighbors (SCAN). For each document, we obtain semantically informative vectors from a large pre-trained language…
Imbalanced node classification is a critical challenge in graph learning, where most existing methods typically utilize Graph Neural Networks (GNNs) to learn node representations. These methods can be broadly categorized into the data-level…
Human coders assign standardized medical codes to clinical documents generated during patients' hospitalization, which is error-prone and labor-intensive. Automated medical coding approaches have been developed using machine learning…
We propose a novel approach to enhance the discriminability of Convolutional Neural Networks (CNN). The key idea is to build a tree structure that could progressively learn fine-grained features to distinguish a subset of classes, by…
Text segmentation, the task of dividing a document into sections, is often a prerequisite for performing additional natural language processing tasks. Existing text segmentation methods have typically been developed and tested using clean,…
Semantic annotations have to satisfy quality constraints to be useful for digital libraries, which is particularly challenging on large and diverse datasets. Confidence scores of multi-label classification methods typically refer only to…
Modal sense classification (MSC) is a special WSD task that depends on the meaning of the proposition in the modal's scope. We explore a CNN architecture for classifying modal sense in English and German. We show that CNNs are superior to…
Classification and clustering have been studied separately in machine learning and computer vision. Inspired by the recent success of deep learning models in solving various vision problems (e.g., object recognition, semantic segmentation)…