SOURCE-LINKED INTELLIGENCE

SAM3-O2D2: Zero-Shot Object Out-of-Distribution Detection by Object Class Prompting of the SAM3-Image Model

arXiv · AI, language, vision and robotics · article · Sep 8, 2026 · UTC

Object detectors have shown remarkable performance in various fields, among these medical imaging, surveillance, and autonomous driving. However, they are prone to overconfidence when encountering unseen objects in real-world deployments, causing potential safety issues. To address this, detecting out-of-distribution (OOD) objects is essential for reliable object detection. Modern approaches leverage the broad semantic knowledge of foundation models such as CLIP for post-hoc few- and zero-shot OOD detection. However, these methods typically perform OOD assessment in feature space, which can be

Read original source ↗ Open in workspace

recordType

paper

region

Global