Related papers: Autonomous Cleaning of Corrupted Scanned Documents…
Modern generative modeling methods have demonstrated strong performance in learning complex data distributions from clean samples. In many scientific and imaging applications, however, clean samples are unavailable, and only noisy or…
Image learning and colorization are hot spots in multimedia domain. Inspired by the learning capability of humans, in this paper, we propose an automatic colorization method with a learning framework. This method can be viewed as a hybrid…
A deraining network can be interpreted as a conditional generator that aims at removing rain streaks from image. Most existing image deraining methods ignore model errors caused by uncertainty that reduces embedding quality. Unlike existing…
We present an autoencoder that leverages learned representations to better measure similarities in data space. By combining a variational autoencoder with a generative adversarial network we can use learned feature representations in the…
Over the last decades, hand-crafted feature extractors have been used to encode image visual properties into feature vectors. Recently, data-driven feature learning approaches have been successfully explored as alternatives for producing…
Automated pavement crack detection is a challenging task that has been researched for decades due to the complicated pavement conditions in real world. In this paper, a supervised method based on deep learning is proposed, which has the…
In supervised learning one wishes to identify a pattern present in a joint distribution $P$, of instances, label pairs, by providing a function $f$ from instances to labels that has low risk $\mathbb{E}_{P}\ell(y,f(x))$. To do so, the…
This work presents a comparison of machine learning algorithms that are implemented to segment the characters of text presented as an image. The algorithms are designed to work on degraded documents with text that is not aligned in an…
Despite recent advances in the field of supervised deep learning for text line segmentation, unsupervised deep learning solutions are beginning to gain popularity. In this paper, we present an unsupervised deep learning method that embeds…
Large language models (LLMs) have notably enhanced the fluency and diversity of machine-generated text. However, this progress also presents a significant challenge in detecting the origin of a given text, and current research on detection…
Autonomous research agents can already run machine learning experiments without human supervision, but many rely on a narrow search strategy: they repeatedly modify one program and keep changes only when they improve the current best…
Recently self-supervised representation learning has drawn considerable attention from the scene text recognition community. Different from previous studies using contrastive learning, we tackle the issue from an alternative perspective,…
Deep neural networks have gained tremendous success in a broad range of machine learning tasks due to its remarkable capability to learn semantic-rich features from high-dimensional data. However, they often require large-scale labelled…
Prior studies have made significant progress in image inpainting guided by either text description or subject image. However, the research on inpainting with flexible guidance or control, i.e., text-only, image-only, and their combination,…
Large Language Models have become the de facto approach to sequence-to-sequence text generation tasks, but for specialized tasks/domains, a pretrained LLM lacks specific capabilities to produce accurate or well-formatted responses.…
When trained on large, unfiltered crawls from the internet, language models pick up and reproduce all kinds of undesirable biases that can be found in the data: they often generate racist, sexist, violent or otherwise toxic language. As…
Removing noise from scanned pages is a vital step before their submission to the optical character recognition (OCR) system. Most available image denoising methods are supervised where the pairs of noisy/clean pages are required. However,…
Recently there has been a lot of work on pruning filters from deep convolutional neural networks (CNNs) with the intention of reducing computations.The key idea is to rank the filters based on a certain criterion (say, l1-norm) and retain…
In this paper, we consider a problem of learning supervised PageRank models, which can account for some properties not considered by classical approaches such as the classical PageRank algorithm. Due to huge hidden dimension of the…
A common approach for improving OCR quality is a post-processing step based on models correcting misdetected characters and tokens. These models are typically trained on aligned pairs of OCR read text and their manually corrected…