Related papers: DELINE8K: A Synthetic Data Pipeline for the Semant…

We present a framework to generate synthetic historical documents with precise ground truth using nothing more than a collection of unlabeled historical images. Obtaining large labeled datasets is often the limiting factor to effectively…

The emergence of text-to-image generative models has revolutionized the field of deepfakes, enabling the creation of realistic and convincing visual content directly from textual descriptions. However, this advancement presents considerably…

Developing document understanding models at enterprise scale requires large, diverse, and well-annotated datasets spanning a wide range of document types. However, collecting such data is prohibitively expensive due to privacy constraints,…

In the ensuing ultra-dense and diverse environment in future \ac{6G} communication networks, it will be critical to optimize network resources via mechanisms that recognize and cater to the diversity, density, and dynamicity of system…

This paper presents a novel approach to generate synthetic dataset for handwritten word recognition systems. It is difficult to recognize handwritten scripts for which sufficient training data is not readily available or it may be expensive…

Document segmentation is a method of rending the document into distinct regions. A document is an assortment of information and a standard mode of conveying information to others. Pursuance of data from documents involves ton of human…

The problem of document structure reconstruction refers to converting digital or scanned documents into corresponding semantic structures. Most existing works mainly focus on splitting the boundary of each element in a single document page,…

Automatic segmentation of retina vessels plays a pivotal role in clinical diagnosis of prevalent eye diseases, such as, Diabetic Retinopathy or Age-related Macular Degeneration. Due to the complex construction of blood vessels, with…

This dissertation addresses visual scene understanding and enhances segmentation performance and generalization, training efficiency of networks, and holistic understanding. First, we investigate semantic segmentation in the context of…

Recently, increasing attention has been drawn to training semantic segmentation models using synthetic data and computer-generated annotation. However, domain gap remains a major barrier and prevents models learned from synthetic data from…

Training data is the key ingredient for deep learning approaches, but difficult to obtain for the specialized domains often encountered in robotics. We describe a synthesis pipeline capable of producing training data for cluttered scene…

In this work, we explore data augmentations for knowledge distillation on semantic segmentation. To avoid over-fitting to the noise in the teacher network, a large number of training examples is essential for knowledge distillation.…

In recent years, instance segmentation has garnered significant attention across various applications. However, training a fully-supervised instance segmentation model requires costly both instance-level and pixel-level annotations. In…

The detection of cracks is a crucial task in monitoring structural health and ensuring structural safety. The manual process of crack detection is time-consuming and subjective to the inspectors. Several researchers have tried tackling this…

We develop an abstractive summarization framework independent of labeled data for multiple heterogeneous documents. Unlike existing multi-document summarization methods, our framework processes documents telling different stories instead of…

We present a generative document-specific approach to character analysis and recognition in text lines. Our main idea is to build on unsupervised multi-object segmentation methods and in particular those that reconstruct images based on a…

We present FasterSeg, an automatically designed semantic segmentation network with not only state-of-the-art performance but also faster speed than current methods. Utilizing neural architecture search (NAS), FasterSeg is discovered from a…

We present a new handwritten text segmentation method by training a convolutional neural network (CNN) in an end-to-end manner. Many conventional methods addressed this problem by extracting connected components and then classifying them.…

Document parsing has recently advanced with multimodal large language models (MLLMs) that directly map document images to structured outputs. Traditional cascaded pipelines depend on precise layout analysis and often fail under casually…

Program similarity has become an increasingly popular area of research with various security applications such as plagiarism detection, author identification, and malware analysis. However, program similarity research faces a few unique…