Related papers: DIVA-DAF: A Deep Learning Framework for Historical…
We present DeepAL, a Python library that implements several common strategies for active learning, with a particular emphasis on deep active learning. DeepAL provides a simple and unified framework based on PyTorch that allows users to…
The advent of modern cloud services along with the huge volume of data produced on a daily basis, have set the demand for fast and efficient data processing. This demand is common among numerous application domains, such as deep learning,…
Handwritten text recognition and optical character recognition solutions show excellent results with processing data of modern era, but efficiency drops with Latin documents of medieval times. This paper presents a deep learning method to…
The main goal of this research is to produce a useful software for United Nations (UN), that could help to speed up the process of qualifying the UN documents following the Sustainable Development Goals (SDGs) in order to monitor the…
Java is very powerful, but in Deep Learning field, its capabilities probably has not been sufficiently exploited. Compared to the Java-based deep-learning-frameworks, the Python-based (PyTorch, TensorFlow, etc) are undoubtedly the…
DeepInverse is an open-source PyTorch-based library for solving imaging inverse problems. The library covers all crucial steps in image reconstruction from the efficient implementation of forward operators (e.g., optics, MRI, tomography),…
The uprising of deep learning methodology and practice in recent years has brought about a severe consequence of increasing carbon footprint due to the insatiable demand for computational resources and power. The field of text analytics…
Though deep learning based scene text detection has achieved great progress, well-trained detectors suffer from severe performance degradation for different domains. In general, a tremendous amount of data is indispensable to train the…
Recent approaches in literature have exploited the multi-modal information in documents (text, layout, image) to serve specific downstream document tasks. However, they are limited by their - (i) inability to learn cross-modal…
Pre-training techniques play a crucial role in deep learning, enhancing models' performance across a variety of tasks. By initially training on large datasets and subsequently fine-tuning on task-specific data, pre-training provides a solid…
Super-Selfish is an easy to use PyTorch framework for image-based self-supervised learning. Features can be learned with 13 algorithms that span from simple classification to more complex state of theart contrastive pretext tasks. The…
Deep learning-based vulnerability detection has shown great performance and, in some studies, outperformed static analysis tools. However, the highest-performing approaches use token-based transformer models, which are not the most…
The use of well-disentangled representations offers many advantages for downstream tasks, e.g. an increased sample efficiency, or better interpretability. However, the quality of disentangled interpretations is often highly dependent on the…
Deep learning algorithms have made many breakthroughs and have various applications in real life. Computational resources become a bottleneck as the data and complexity of the deep learning pipeline increases. In this paper, we propose…
In this paper, we introduce a fully convolutional network for the document layout analysis task. While state-of-the-art methods are using models pre-trained on natural scene images, our method Doc-UFCN relies on a U-shaped model trained…
This work presents the Video Platform for PyTorch (ViP), a deep learning-based framework designed to handle and extend to any problem domain based on videos. ViP supports (1) a single unified interface applicable to all video problem…
The document layout analysis (DLA) aims to split the document image into different interest regions and understand the role of each region, which has wide application such as optical character recognition (OCR) systems and document…
This work is a rigorous development of a complete and general-purpose deep learning framework from the ground up. The fundamental components of deep learning - automatic differentiation and gradient methods of optimizing multivariable…
In this paper, we present a novel approach to perform deep neural networks layer-wise weight initialization using Linear Discriminant Analysis (LDA). Typically, the weights of a deep neural network are initialized with: random values,…
Foundation models and self-supervised learning (SSL) have become central to modern AI, yet research in this area remains hindered by complex codebases, redundant re-implementations, and the heavy engineering burden of scaling experiments.…