Related papers: The HASYv2 dataset
The COS Legacy Archive Spectroscopic SurveY (CLASSY) is designed to provide the community with a spectral atlas of 45 nearby star-forming galaxies which were chosen to cover similar properties as those seen at high-z (z>6). The prime high…
In this paper, we describe and present the first dataset of source code plagiarism specifically aimed at contest plagiarism. The dataset contains 251 pairs of plagiarized solutions of competitive programming tasks in Java, as well as 660…
Multiple-instance learning is a subset of weakly supervised learning where labels are applied to sets of instances rather than the instances themselves. Under the standard assumption, a set is positive only there is if at least one instance…
Classification is a fundamental problem in machine learning and data mining. During the past decades, numerous classification methods have been presented based on different principles. However, most existing classifiers cast the…
We introduce ninfty, a header-only C++ library distributed under an MIT Open Source License designed for the study of enumeration problems arising in homotopical combinatorics. The ninfty repository moreover contains a folder with data…
Instance detection (InsDet) is a long-lasting problem in robotics and computer vision, aiming to detect object instances (predefined by some visual examples) in a cluttered scene. Despite its practical significance, its advancement is…
We present a new dataset for form understanding in noisy scanned documents (FUNSD) that aims at extracting and structuring the textual content of forms. The dataset comprises 199 real, fully annotated, scanned forms. The documents are noisy…
This document describes a novel learning algorithm that classifies "bags" of instances rather than individual instances. A bag is labeled positive if it contains at least one positive instance (which may or may not be specifically…
Exact similarity search over large collections of data series is a fundamental operation in modern applications, yet existing solutions are often fragmented, specialized, or tailored to specific execution environments. In this paper, we…
HAL is an open-source framework for gate-level netlist analysis, an integral step in hardware reverse engineering. It provides analysts with an interactive GUI, an extensible plugin system, and APIs in both C++ and Python for rapid…
Saliency modeling has been an active research area in computer vision for about two decades. Existing state of the art models perform very well in predicting where people look in natural scenes. There is, however, the risk that these models…
Misleading visualizations are a potent driver of misinformation on social media and the web. By violating chart design principles, they distort data and lead readers to draw inaccurate conclusions. Prior work has shown that both humans and…
The recent rise in the popularity of large language models has spurred the development of extensive code datasets needed to train them. This has left limited code available for collection and use in the downstream investigation of specific…
Network Intrusion Detection Systems (NIDSs) are important tools for the protection of computer networks against increasingly frequent and sophisticated cyber attacks. Recently, a lot of research effort has been dedicated to the development…
Automatic identification of screw types is important for industrial automation, robotics, and inventory management. However, publicly available datasets for screw classification are scarce, particularly for controlled single-object…
Despite the fast progress in training specialized models for various tasks, learning a single general model that works well for many tasks is still challenging for computer vision. Here we introduce multi-task self-training (MuST), which…
Neurosymbolic (NeSy) frameworks combine neural representations and learning with symbolic representations and reasoning. Combining the reasoning capacities, explainability, and interpretability of symbolic processing with the flexibility…
Understanding the performance of machine learning models across diverse data distributions is critically important for reliable applications. Motivated by this, there is a growing focus on curating benchmark datasets that capture…
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…
In this manuscript, we demonstrate, using several regression techniques, that the remaining independent Hodge numbers of complete intersection Calabi-Yau four-folds and five-folds can be machine learned from $h^{1,1}$ and $h^{2,1}$.…