Related papers: Data Leakage Detection and De-duplication in Large…

Large training data and expensive model tweaking are standard features of deep learning for images. As a result, data owners often utilize cloud resources to develop large-scale complex models, which raises privacy concerns. Existing…

Active learning aims to select the minimum amount of data to train a model that performs similarly to a model trained with the entire dataset. We study the potential of active learning for image segmentation in underwater infrastructure…

Identifying the locations and footprints of buildings is vital for many practical and scientific purposes. Such information can be particularly useful in developing regions where alternative data sources may be scarce. In this work, we…

Illegal landfills are posing as a hazardous threat to people all over the world. Due to the arduous nature of manually identifying the location of landfill, many landfills go unnoticed by authorities and later cause dangerous harm to people…

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…

Link prediction is a fundamental problem in network science, aiming to infer potential or missing links based on observed network structures. With the increasing adoption of parameterized models, the rigor of evaluation protocols has become…

In existing splicing forgery datasets, the insufficient semantic variety of spliced regions causes trained detection models to overfit semantic features rather than learn genuine splicing traces. Meanwhile, the lack of a reasonable…

Deep learning models, particularly Long Short-Term Memory (LSTM) networks, are widely used in time series forecasting due to their ability to capture complex temporal dependencies. However, evaluation integrity is often compromised by data…

Aerial imagery can be used for important work on a global scale. Nevertheless, the analysis of this data using neural network architectures lags behind the current state-of-the-art on popular datasets such as PASCAL VOC, CityScapes and…

Despite recent advances in Generative Adversarial Networks (GANs), with special focus to the Deepfake phenomenon there is no a clear understanding neither in terms of explainability nor of recognition of the involved models. In particular,…

In software development environments, code quality is crucial. This study aims to assist Machine Learning (ML) engineers in enhancing their code by identifying and correcting Data Leakage issues within their models. Data Leakage occurs when…

High-resolution satellite imagery have been increasingly used on remote sensing classification problems. One of the main factors is the availability of this kind of data. Even though, very little effort has been placed on the zebra crossing…

Image space feature detection is the act of selecting points or parts of an image that are easy to distinguish from the surrounding image region. By combining a repeatable point detection with a descriptor, parts of an image can be matched…

Training neural networks usually require large numbers of sensitive training data, and how to protect the privacy of training data has thus become a critical topic in deep learning research. InstaHide is a state-of-the-art scheme to protect…

The deep neural networks used in modern computer vision systems require enormous image datasets to train them. These carefully-curated datasets typically have a million or more images, across a thousand or more distinct categories. The…

We study an important, yet largely unexplored problem of large-scale cross-modal visual localization by matching ground RGB images to a geo-referenced aerial LIDAR 3D point cloud (rendered as depth images). Prior works were demonstrated on…

The accuracy and robustness of machine learning models against adversarial attacks are significantly influenced by factors such as training data quality, model architecture, the training process, and the deployment environment. In recent…

Does the training of large language models potentially infringe upon code licenses? Furthermore, are there any datasets available that can be safely used for training these models without violating such licenses? In our study, we assess the…

While invaluable for many computer vision applications, decomposing a natural image into intrinsic reflectance and shading layers represents a challenging, underdetermined inverse problem. As opposed to strict reliance on conventional…

In machine learning, research has traditionally focused on model development, with relatively less attention paid to training data. As model architectures have matured and marginal gains from further refinements diminish, data quality has…