Detection, segmentation, depth and recognition research, plus the vision backbones that keep displacing the last generation.
arXiv:2608. 16810v1 Announce Type: cross Abstract: Identifying and representing object instances such as cells or nuclei is a common task in microscopy image analysis.
arXiv:2608. 14600v1 Announce Type: cross Abstract: We present a demonstration for generative multicasting with on-device, intent-aware semantic decomposition.
arXiv:2608. 16268v1 Announce Type: cross Abstract: Medical foundation models improve generalization when training AI models with limited labeled data, but remain confined to a single specialty, such as pathology or radiology, and to either sparse or dense outputs, such as classification or segmentation.
arXiv:2509. 11218v2 Announce Type: replace-cross Abstract: Spatial transformations such as rotation and scale obscure the morphological cues needed for accurate image classification.
arXiv:2608. 15915v1 Announce Type: cross Abstract: Lung cancer remains the leading cause of cancer-related mortality worldwide, while histopathological diagnosis is often affected by inter-observer variability and the substantial workload associated with manual slide examination.
arXiv:2510. 15042v3 Announce Type: replace-cross Abstract: In the 3D medical image domain, vision-language pre-training is used to create vision-language encoders (VLEs) that can support radiologists by retrieving patients with similar abnormalities, predicting likelihoods of abnormality, or, with downstream adaptation, generating radiological reports.
arXiv:2608. 15090v1 Announce Type: cross Abstract: Studies of industrial visual inspection commonly report the area under the receiver operating characteristic curve (AUROC) and the overlap between anomaly maps and defect masks.
arXiv:2608. 15731v1 Announce Type: cross Abstract: Deep Neural Networks (DNNs) deployed in high-risk domains, such as healthcare and autonomous driving, must be not only accurate but also understandable to ensure user trust.
Whole-slide image (WSI) analysis remains computationally challenging due to the extremely large spatial resolution of slides and the sparse distribution of tumour regions. We propose an end-to-end reinforcement learning framework for sequential tumour segmentation directly on WSIs.
Unsupervised Domain Adaptation for Adverse Weather Semantic Segmentation (UDA-ASS) aims to transfer semantic knowledge from labeled normal-weather images to unlabeled adverse environments. Existing approaches implicitly assume that restoration and segmentation provide mutually beneficial guidance.
Referring Video Object Segmentation (RVOS) aims to segment referred objects at the pixel level in video sequences based on natural language descriptions. Existing methods typically introduce motion information within a unified cross-modal temporal modeling framework, where language cues are used for target localization and segmentation.
arXiv:2608. 14130v1 Announce Type: cross Abstract: Computer vision models for generated facial content, such as face editing and privacy protection, increasingly affect people, requiring similarity metrics that serve as faithful proxies for human perception.
arXiv:2608. 13690v1 Announce Type: cross Abstract: Medical image segmentation is still largely treated as a vision-only problem, although clinical interpretation often relies on textual knowledge of anatomy, location, appearance, and surrounding context.
arXiv:2608. 14058v1 Announce Type: cross Abstract: Seismic facies segmentation has emerged as a significant challenge in geophysics, requiring robust methods and systems to effectively identify geologically analogous facies with limited labeled data.
arXiv:2608. 13584v1 Announce Type: cross Abstract: UltraArUco - a lightweight multilingual library and framework for low-latency, real-time marker-based tracking in mobile augmented reality.
arXiv:2603. 07571v3 Announce Type: replace-cross Abstract: Out-of-distribution (OOD) detection is critical in safety-sensitive applications.
arXiv:2608. 14373v1 Announce Type: new Abstract: The symmetries of a learning task have become an important factor in designing modern deep learning solutions.
arXiv:2608. 13660v1 Announce Type: cross Abstract: Medical image segmentation models are typically trained under the assumption that all data are available simultaneously.
arXiv:2512. 14732v3 Announce Type: replace-cross Abstract: Incidental findings in CT scans, though often benign, can have significant clinical implications and should be reported following established guidelines.
Camera-based object detectors are vulnerable to physical adversarial attacks designed to suppress detections. While adversarial training and input purification offer some protection, they often overfit to specific attack distributions and fail on adaptive adversaries.