Related papers: User Guide to UVIT Data Reduction
This paper investigates the performance of the Contrastive Language-Image Pre-training (CLIP) when scaled down to limited computation budgets. We explore CLIP along three dimensions: data, architecture, and training strategies. With regards…
Vision Transformers (ViTs) have become ubiquitous in computer vision. Despite their success, ViTs lack inductive biases, which can make it difficult to train them with limited data. To address this challenge, prior studies suggest training…
User interface (UI) design is a difficult yet important task for ensuring the usability, accessibility, and aesthetic qualities of applications. In our paper, we develop a machine-learned model, UIClip, for assessing the design quality and…
Visual analytics systems such as Tableau are increasingly popular for interactive data exploration. These tools, however, do not currently assist users with detecting or resolving potential data quality problems including the well-known…
Although deep learning models have had great success in natural language processing and computer vision, we do not observe comparable improvements in the case of tabular data, which is still the most common data type used in biological,…
The last 15 years have seen a surge of new multi-chip optical and near-IR imagers. While some of them are accompanied by specific reduction pipelines, user-friendly and generic reduction tools are uncommon. In this paper I introduce THELI,…
Contrastive Language-Image Pre-training (CLIP) has drawn increasing attention recently for its transferable visual representation learning. However, due to the semantic gap within datasets, CLIP's pre-trained image-text alignment becomes…
While dataset condensation effectively enhances training efficiency, its application in on-device scenarios brings unique challenges. 1) Due to the fluctuating computational resources of these devices, there's a demand for a flexible…
Domain-specific image collections present potential value in various areas of science and business but are often not curated nor have any way to readily extract relevant content. To employ contemporary supervised image analysis methods on…
In this article we report the release of a new program for batch processing and visualization of powder diffraction data. The program, which is free-of-charge for non-commercial use and can be obtained with its detailed documentation from…
Lidar sensors are widely used in various applications, ranging from scientific fields over industrial use to integration in consumer products. With an ever growing number of different driver assistance systems, they have been introduced to…
We introduce UViM, a unified approach capable of modeling a wide range of computer vision tasks. In contrast to previous models, UViM has the same functional form for all tasks; it requires no task-specific modifications which require…
Clustering is a popular data mining technique that aims to partition an input space into multiple homogeneous regions. There exist several clustering algorithms in the literature. The performance of a clustering algorithm depends on its…
Learning from imperfect data becomes an issue in many industrial applications after the research community has made profound progress in supervised learning from perfectly annotated datasets. The purpose of the Learning from Imperfect Data…
A typical problem in Visual Analytics is that users are highly trained experts in their application domains, but have mostly no experience in using VA systems. Thus, users often have difficulties interpreting and working with visual…
EUTelescope is arguably the most used software to reconstruct tracks from telescope data. This guide explains how to install a version adapted for the reconstruction of ITk Strip test beam data. In this version, an example of such…
Constraint programming is used for a variety of real-world optimisation problems, such as planning, scheduling and resource allocation problems. At the same time, one continuously gathers vast amounts of data about these problems. Current…
Machine learning-based software vulnerability detection requires high-quality datasets, which is essential for training effective models. To address challenges related to data label quality, diversity, and comprehensiveness, we constructed…
For instruments with many occasional users, it is important to have easy to use software. To support the frequent users it is important to be flexible. Using a scripting language to design a GUI and exposing it to the user allows us to do…
A huge amount of medical data is generated every day, which presents a challenge in analysing these data. The obvious solution to this challenge is to reduce the amount of data without information loss. Dimension reduction is considered the…