# Unsupervised Recognition of Unknown Objects for Open-World Object Detection Source: [Unsupervised Recognition of Unknown Objects for Open-World Object Detection]() Collection index: [llms.txt]() Data updated: 2025-10-27T06:25:24.889Z Authors: Ruohuan Fang, Guansong Pang, Lei Zhou, Xiao Bai, Jin Zheng Published: 2023-08-31T08:17:29.000Z ## Abstract Open-World Object Detection (OWOD) extends object detection problem to a realistic and dynamic scenario, where a detection model is required to be capable of detecting both known and unknown objects and incrementally learning newly introduced knowledge. Current OWOD models, such as ORE and OW-DETR, focus on pseudo-labeling regions with high objectness scores as unknowns, whose performance relies heavily on the supervision of known objects. While they can detect the unknowns that exhibit similar features to the known objects, they suffer from a severe label bias problem that they tend to detect all regions (including unknown object regions) that are dissimilar to the known objects as part of the background. To eliminate the label bias, this paper proposes a novel approach that learns an unsupervised discriminative model to recognize true unknown objects from raw pseudo labels generated by unsupervised region proposal methods. The resulting model can be further refined by a classification-free self-training method which iteratively extends pseudo unknown objects to the unlabeled regions. Experimental results show that our method 1) significantly outperforms the prior SOTA in detecting unknown objects while maintaining competitive performance of detecting known object classes on the MS COCO dataset, and 2) achieves better generalization ability on the LVIS and Objects365 datasets. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Incremental Object Detection on MS-COCO Task 1](): Incremental Object Detection; MS-COCO Task 1; mAP@C: 74.3. - [Incremental Object Detection on MS-COCO Task 2](): Incremental Object Detection; MS-COCO Task 2; mAP@P: 68. - [Incremental Object Detection on MS-COCO Task 4](): Incremental Object Detection; MS-COCO Task 4; mAP@A: 41.2. - [Incremental Object Detection on MS-COCO Task 3](): Incremental Object Detection; MS-COCO Task 3; mAP@P: 50.2. ## Original sources and implementation [Original paper]() [PDF]()