Neighborhood-Aware Representation Learning for Open-World Object Detection

Open World Object Detection (OWOD) extends conventional object detection beyond a fixed label space, enabling unknown object discovery and incremental learning of new classes. Representative objectness-based approaches commonly rely on global probabilistic foreground modeling or reduce the coupling between objectness and known class prediction. However, they typically treat known class discrimination and foreground modeling separately, leaving the connection between the two objectives underexplored. We therefore introduce Prototype Relations for Open World object detection (PROW), a neighborhood-aware representation learning framework that exploits neighborhood relations among known class prototypes as a shared structure for local class discrimination and multi-component foreground modeling. PROW maintains a dynamic graph over class prototypes, with neighborhood relations updated from matched positive queries. The graph identifies locally confusable prototypes as informative negatives for local class discrimination, while the same graph organizes class prototypes into multiple neighborhood-conditioned foreground components. For each query, PROW selects the most compatible foreground component to estimate class-independent objectness. In subsequent tasks, confidence-filtered pseudo-labels from the previous detector and replay samples provide complementary supervision to preserve previously learned knowledge. Compared with the best prior results, PROW achieves absolute gains of $2.4$-$8.1$ points in unknown object discovery, with a $39\%$ reduction in confusion between known and unknown objects.