Related papers: Seeing without Looking: Analysis Pipeline for Chil…

Background: The segment-anything model (SAM), introduced in April 2023, shows promise as a benchmark model and a universal solution to segment various natural images. It comes without previously-required re-training or fine-tuning specific…

The pursuit of fairness in machine learning (ML), ensuring that the models do not exhibit biases toward protected demographic groups, typically results in a compromise scenario. This compromise can be explained by a Pareto frontier where…

Sharpness-Aware Minimization (SAM) has emerged as a promising approach for effectively reducing the generalization error. However, SAM incurs twice the computational cost compared to base optimizer (e.g., SGD). We propose Asymptotic…

Modern machine learning systems use models trained on ever-growing corpora. Typically, metadata such as ownership, access control, or licensing information is ignored during training. Instead, to mitigate privacy risks, we rely on generic…

Instance segmentation of prohibited items in security X-ray images is a critical yet challenging task. This is mainly caused by the significant appearance gap between prohibited items in X-ray images and natural objects, as well as the…

Cybersecurity analysts work on large communication data sets to perform investigative analysis by painstakingly going over thousands of email conversations to find potential scamming activities and the network of cyber scammers.…

Vision-Language Models (VLMs) are pretrained on large, diverse, and noisy web-crawled datasets. This underscores the critical need for dataset pruning, as the quality of these datasets is strongly correlated with the performance of VLMs on…

With the arrival of a number of wide-field snapshot image-plane radio transient surveys, there will be a huge influx of images in the coming years making it impossible to manually analyse the datasets. Automated pipelines to process the…

Unsupervised (US) video anomaly detection (VAD) in surveillance applications is gaining more popularity recently due to its practical real-world applications. As surveillance videos are privacy sensitive and the availability of large-scale…

Purpose: Automated ultrasound image analysis is challenging due to anatomical complexity and limited annotated data. To tackle this, we take a data-centric approach, assembling the largest public ultrasound segmentation dataset and training…

Segment Anything Model (SAM) is an advanced foundational model for image segmentation, which is gradually being applied to remote sensing images (RSIs). Due to the domain gap between RSIs and natural images, traditional methods typically…

Analyzing and finding anomalies in multi-dimensional datasets is a cumbersome but vital task across different domains. In the context of financial fraud detection, analysts must quickly identify suspicious activity among transactional data.…

Using extensive training data from SA-1B, the Segment Anything Model (SAM) has demonstrated exceptional generalization and zero-shot capabilities, attracting widespread attention in areas such as medical image segmentation and remote…

Textual data used to train large language models (LLMs) exhibits multifaceted bias manifestations encompassing harmful language and skewed demographic distributions. Regulations such as the European AI Act require identifying and mitigating…

Training large vision-language models requires extensive, high-quality image-text pairs. Existing web-scraped datasets, however, are noisy and lack detailed image descriptions. To bridge this gap, we introduce PixelProse, a comprehensive…

Reliable pseudo-labels from unlabeled data play a key role in semi-supervised object detection (SSOD). However, the state-of-the-art SSOD methods all rely on pseudo-labels with high confidence, which ignore valuable pseudo-labels with lower…

On the modern web, trackers and advertisers frequently construct and monetize users' detailed behavioral profiles without consent. Despite various studies on web tracking mechanisms and advertisements, there has been no rigorous study…

Privacy leakage in LLM agents is often studied through individual storage or execution components, such as memory modules, retrieval pipelines, or tool-mediated artifacts. However, these settings are typically analyzed in isolation, making…

Labelled image datasets have played a critical role in high-level image understanding. However, the process of manual labelling is both time-consuming and labor intensive. To reduce the cost of manual labelling, there has been increased…

Image-level weakly supervised semantic segmentation is a challenging problem that has been deeply studied in recent years. Most of advanced solutions exploit class activation map (CAM). However, CAMs can hardly serve as the object mask due…