OW-DETR: Open-world Detection Transformer
Akshita Gupta, Sanath Narayan, K J Joseph, Salman Khan, Fahad Shahbaz, Khan, Mubarak Shah

TL;DR
OW-DETR is a novel transformer-based framework designed for open-world object detection, capable of identifying known and unknown objects, and incrementally learning new classes with improved accuracy over previous methods.
Contribution
The paper introduces OW-DETR, an end-to-end transformer model with attention-driven pseudo-labeling, novelty classification, and objectness scoring for open-world detection, outperforming prior approaches.
Findings
Outperforms OWOD approach ORE with 1.8%-3.3% higher unknown recall on MS-COCO.
Achieves state-of-the-art results on incremental object detection on PASCAL VOC.
Explicitly encodes multi-scale contextual information for better discrimination.
Abstract
Open-world object detection (OWOD) is a challenging computer vision problem, where the task is to detect a known set of object categories while simultaneously identifying unknown objects. Additionally, the model must incrementally learn new classes that become known in the next training episodes. Distinct from standard object detection, the OWOD setting poses significant challenges for generating quality candidate proposals on potentially unknown objects, separating the unknown objects from the background and detecting diverse unknown objects. Here, we introduce a novel end-to-end transformer-based framework, OW-DETR, for open-world object detection. The proposed OW-DETR comprises three dedicated components namely, attention-driven pseudo-labeling, novelty classification and objectness scoring to explicitly address the aforementioned OWOD challenges. Our OW-DETR explicitly encodes…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsAdvanced Neural Network Applications · Domain Adaptation and Few-Shot Learning · Multimodal Machine Learning Applications
