SOTAVerified

Open World Object Detection

Open World Object Detection is a computer vision problem where a model is tasked to: 1) identify objects that have not been introduced to it as `unknown', without explicit supervision to do so, and 2) incrementally learn these identified unknown categories without forgetting previously learned classes, when the corresponding labels are progressively received.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 31–40 of 50 papers

TitleStatusHype
Detecting Open World Objects via Partial Attribute Assignment—0
SAM2Auto: Auto Annotation Using FLASH—0
DetCLIP: Dictionary-Enriched Visual-Concept Paralleled Pre-training for Open-world Detection—0
Decoupled PROB: Decoupled Query Initialization Tasks and Objectness-Class Learning for Open World Object Detection—0
Finding Dino: A plug-and-play framework for unsupervised detection of out-of-distribution objects using prototypes—0
YOLOOC: YOLO-based Open-Class Incremental Object Detection with Novel Class Discovery—0
USD: Unknown Sensitive Detector Empowered by Decoupled Objectness and Segment Anything Model—0
BSDP: Brain-inspired Streaming Dual-level Perturbations for Online Open World Object Detection—0
UADet: A Remarkably Simple Yet Effective Uncertainty-Aware Open-Set Object Detection Framework—0
VL-SAM-V2: Open-World Object Detection with General and Specific Query Fusion—0
Show:102550
← PrevPage 4 of 5Next →

No leaderboard results yet.