Related papers: Advancing Post-OCR Correction: A Comparative Study…

In cross-domain retrieval, a model is required to identify images from the same semantic category across two visual domains. For instance, given a sketch of an object, a model needs to retrieve a real image of it from an online store's…

This paper explores the use of a learned classifier for post-OCR text correction. Experiments with the Arabic language show that this approach, which integrates a weighted confusion matrix and a shallow language model, improves the vast…

Visual grouping -- operationalized through tasks such as instance segmentation, visual grounding, and object detection -- enables applications ranging from robotic perception to photo editing. These fundamental problems in computer vision…

A common and effective means for improving language model capabilities involves finetuning a ``student'' language model's parameters on generations from a more proficient ``teacher'' model. Termed ``synthetic data'', these generations are…

The generation of synthetic data is an essential tool to study complex systems, allowing for example to test models of these in precisely controlled settings, or to parametrize simulation models when data is missing. This paper focuses on…

Progress in neural grammatical error correction (GEC) is hindered by the lack of annotated training data. Sufficient amounts of high-quality manually annotated data are not available, so recent research has relied on generating synthetic…

Malware attacks have a significant negative impact on organizations of varied scales in the field of cybersecurity. Recently, malware researchers have increasingly turned to machine learning techniques to combat sophisticated obfuscation…

Synthetic image data generation represents a promising avenue for training deep learning models, particularly in the realm of transfer learning, where obtaining real images within a specific domain can be prohibitively expensive due to…

Is it possible to build a general and automatic natural language generation (NLG) evaluation metric? Existing learned metrics either perform unsatisfactorily or are restricted to tasks where large human rating data is already available. We…

The emergence of generative AI models has dramatically expanded the availability and use of synthetic data across scientific, industrial, and policy domains. While these developments open new possibilities for data analysis, they also raise…

Synthetic data is a standard component in training large language models, yet systematic comparisons across design dimensions, including rephrasing strategy, generator model, and source data, remain absent. We conduct extensive controlled…

Stereo matching is an important problem in computer vision which has drawn tremendous research attention for decades. Recent years, data-driven methods with convolutional neural networks (CNNs) are continuously pushing stereo matching to…

As machine learning models continue to swiftly advance, calibrating their performance has become a major concern prior to practical and widespread implementation. Most existing calibration methods often negatively impact model accuracy due…

Quantization is a widely adopted technique for deep neural networks to reduce the memory and computational resources required. However, when quantized, most models would need a suitable calibration process to keep their performance intact,…

Nowadays, the use of synthetic data has gained popularity as a cost-efficient strategy for enhancing data augmentation for improving machine learning models performance as well as addressing concerns related to sensitive data privacy.…

Synthetic data is emerging as a substitute for authentic data to solve ethical and legal challenges in handling authentic face data. The current models can create real-looking face images of people who do not exist. However, it is a known…

Existing scene text recognition (STR) methods struggle to recognize challenging texts, especially for artistic and severely distorted characters. The limitation lies in the insufficient exploration of character morphologies, including the…

In recent years, deep learning models have resulted in a huge amount of progress in various areas, including computer vision. By nature, the supervised training of deep models requires a large amount of data to be available. This ideal case…

The issues that must be considered regarding the utilization of synthetic data generated through LLMs for multilabel patent classification include (i) when the use of such data may help and (ii) why. Indeed, the former part appropriately…

Semantic segmentation networks require large amounts of pixel-level annotated data, which are costly to obtain for real-world images. Computer graphics engines can generate synthetic images alongside their ground-truth annotations. However,…