Related papers: User Guide to UVIT Data Reduction

Real-world data for classification is often labeled by multiple annotators. For analyzing such data, we introduce CROWDLAB, a straightforward approach to utilize any trained classifier to estimate: (1) A consensus label for each example…

With growing demands for data privacy and model robustness, graph unlearning (GU), which erases the influence of specific data on trained GNN models, has gained significant attention. However, existing exact unlearning methods suffer from…

The image compression model has long struggled with adaptability and generalization, as the decoded bitstream typically serves only human or machine needs and fails to preserve information for unseen visual tasks. Therefore, this paper…

Multidimensional data analysis has become increasingly important in many fields, mainly due to current vast data availability and the increasing demand to extract knowledge from it. In most applications, the role of the final user is…

Contrastive Language-Image Pre-training (CLIP) is an approach that has advanced research and applications in computer vision, fueling modern recognition systems and generative models. We believe that the main ingredient to the success of…

Underwater object detection (UOD) is vital to diverse marine applications, including oceanographic research, underwater robotics, and marine conservation. However, UOD faces numerous challenges that compromise its performance. Over the…

Cognitive-Driven Development (CDD) is a coding design technique that aims to reduce the cognitive effort that developers place in understanding a given code unit (e.g., a class). By following CDD design practices, it is expected that the…

Mask-based annotation of medical images, especially for 3D data, is a bottleneck in developing reliable machine learning models. Using minimal-labor user interactions (UIs) to guide the annotation is promising, but challenges remain on best…

The focus of this study is on Unsupervised Continual Learning (UCL), as it presents an alternative to Supervised Continual Learning which needs high-quality manual labeled data. The experiments under the UCL paradigm indicate a phenomenon…

Federated Unlearning (FU) aims to delete specific training data from an ML model trained using Federated Learning (FL). We introduce QuickDrop, an efficient and original FU method that utilizes dataset distillation (DD) to accelerate…

Continual learning is a process that involves training learning agents to sequentially master a stream of tasks or classes without revisiting past data. The challenge lies in leveraging previously acquired knowledge to learn new tasks…

The Euclid satellite is an ESA mission scheduled for launch in September 2023. To optimally perform critical stages of the data reduction, such as object detection and morphology determination, a new and modern software package was…

Feature reduction is an important concept which is used for reducing dimensions to decrease the computation complexity and time of classification. Since now many approaches have been proposed for solving this problem, but almost all of them…

As a special type of transformer, Vision Transformers (ViTs) are used to various computer vision applications (CV), such as image recognition. There are several potential problems with convolutional neural networks (CNNs) that can be solved…

Vision Transformers (ViTs) have revolutionized computer vision tasks with their exceptional performance. However, the introduction of privacy regulations such as GDPR and CCPA has brought new challenges to them. These laws grant users the…

To improve the usability of a revision history, change untangling, which reconstructs the history to ensure that changes in each commit belong to one intentional task, is important. Although there are several untangling approaches based on…

Several large-scale video datasets have been published these years and have advanced the area of video understanding. However, the newly emerged user-generated short-form videos have rarely been studied. This paper presents USV, the…

For efficiency of the large production tasks distributed worldwide, it is essential to provide shared production management tools comprised of integratable and interoperable services. To enhance the ATLAS DC1 production toolkit, we…

Weakly supervised video anomaly detection (WSVAD) is a challenging task since only video-level labels are available for training. In previous studies, the discriminative power of the learned features is not strong enough, and the data…

The use of integral field spectroscopy is becoming increasingly popular, hovewer data reduction is still a difficult process. Here I present a step-by-step guide to the reduction of integral field data acquired with the Gemini Multi-Object…