相关论文: Autonomous Cleaning of Corrupted Scanned Documents…

Graphs and networks are a key research tool for a variety of science fields, most notably chemistry, biology, engineering and social sciences. Modeling and generation of graphs with efficient sampling is a key challenge for graphs. In…

State-of-the-art generative models exhibit powerful image-generation capabilities, introducing various ethical and legal challenges to service providers hosting these models. Consequently, Content Removal Techniques (CRTs) have emerged as a…

A program is characterized by its input model, and a formal input model can be of use in diverse areas including vulnerability analysis, reverse engineering, fuzzing and software testing, clone detection and refactoring. Unfortunately,…

Benchmark datasets in computer vision often contain off-topic images, near duplicates, and label errors, leading to inaccurate estimates of model performance. In this paper, we revisit the task of data cleaning and formalize it as either a…

In this paper, we introduce a reproducible cleaning process for the text extracted from PDFs using n-gram models. Our approach compares the originally extracted text with the text generated from, or expected by, these models using earlier…

With unified model-generated images now widespread online, attributing their model of origin offers a path toward transparency and deeper insight into the characteristic behaviors of individual models. Prior work has explored provenance in…

Fonts can convey profound meanings of words in various forms of glyphs. Without typography knowledge, manually selecting an appropriate font or designing a new font is a tedious and painful task. To allow users to explore vast font styles…

Parametric and non-parametric classifiers often have to deal with real-world data, where corruptions like noise, occlusions, and blur are unavoidable - posing significant challenges. We present a probabilistic approach to classify strongly…

We propose Autolearn, a framework that enables language models to learn from documents they read, with no external supervision. Passages that produce anomalously high per-token loss are flagged, verified through a self-generated Q&A chain,…

As the amount of textual data has been rapidly increasing over the past decade, efficient similarity search methods have become a crucial component of large-scale information retrieval systems. A popular strategy is to represent original…

The robustness to noise and outliers is an important issue in linear representation in real applications. We focus on the problem that samples are grossly corrupted, which is also the 'sample specific' corruptions problem. A reasonable…

Training generative models that capture rich semantics of the data and interpreting the latent representations encoded by such models are very important problems in un-/self-supervised learning. In this work, we provide a simple algorithm…

This paper presents an improved LLM based model for Grammatical Error Detection (GED), which is a very challenging and equally important problem for many applications. The traditional approach to GED involved hand-designed features, but…

An approach to utilize recent advances in deep generative models for anomaly detection in a granular (continuous) sense on a real-world image dataset with quality issues is detailed using recent normalizing flow models, with implications in…

Our work focuses on unsupervised and generative methods that address the following goals: (a) learning unsupervised generative representations that discover latent factors controlling image semantic attributes, (b) studying how this ability…

Front end of data collection and loading into database manually may cause potential errors in data sets and a very time consuming process. Scanning of a data document in the form of an image and recognition of corresponding information in…

Automatic detection of font size finds many applications in the area of intelligent OCRing and document image analysis, which has been traditionally practiced over uncompressed documents, although in real life the documents exist in…

Training deep neural models in the presence of corrupted supervision is challenging as the corrupted data points may significantly impact the generalization performance. To alleviate this problem, we present an efficient robust algorithm…

Data is inherently dirty and there has been a sustained effort to come up with different approaches to clean it. A large class of data repair algorithms rely on data-quality rules and integrity constraints to detect and repair the data. A…

This work presents a method for visual text recognition without using any paired supervisory data. We formulate the text recognition task as one of aligning the conditional distribution of strings predicted from given text images, with…