arXiv:2608. 08308v1 Announce Type: cross Abstract: Modern vision systems must operate in "open-world" settings, where models must recognize known categories and detect unseen or anomalous content.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.
arXiv:2609.24204v1 Announce Type: new Abstract: Visual segmentation systems encounter objects outside their training distribution during real-world deployment, hindering reliable autonomous systems t...
Visual segmentation systems encounter objects outside their training distribution during real-world deployment, hindering reliable autonomous systems that depend on scene parsing in the perception sta...
Open-world object detection (OWOD) requires a detector to recognize known categories, discover unnamed objects from unseen categories, and incrementally learn newly annotated classes. PROB improves unknown discovery by modeling class-agnostic probabilistic objectness in the decoder-query space.
arXiv:2607. 22212v1 Announce Type: cross Abstract: Visual anomaly detection requires adaptive representations and reliable decision boundaries, particularly when anomalous training samples are scarce and class distributions are highly imbalanced.
arXiv:2605. 07821v2 Announce Type: replace-cross Abstract: Out-of-distribution (OOD) detection is crucial for ensuring the reliability of deep learning models.
Background-Free Objectness Learning (B-FOR) is a dense, class‑agnostic detection framework that learns objectness without treating unlabeled regions as background. It predicts multi‑scale object‑center and scale fields, using spatially structured soft targets to supervise only reliable annotated areas and introduces displacement‑aware scale fields to model object extent. Experiments on PASCAL VOC, MS‑COCO, and Open Images show B‑FOR improves recall by over +10 AR points compared to prior class‑agnostic baselines, with ablation studies confirming the importance of localized supervision and displacement‑aware scaling.