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
Unknown Sniffer for Object Detection: Don't Turn a Blind Eye to Unknown ObjectsCode1
Detecting Everything in the Open World: Towards Universal Object DetectionCode2
Detecting the open-world objects with the help of the BrainCode1
Open-World Object Detection via Discriminative Class Prototype Learning—0
CAT: LoCalization and IdentificAtion Cascade Detection Transformer for Open-World Object Detection—0
Annealing-Based Label-Transfer Learning for Open World Object DetectionCode1
GOOD: Exploring Geometric Cues for Detecting Objects in an Open WorldCode1
Open World DETR: Transformer based Open World Object Detection—0
PROB: Probabilistic Objectness for Open World Object DetectionCode1
DetCLIP: Dictionary-Enriched Visual-Concept Paralleled Pre-training for Open-world Detection—0
Show:102550
← PrevPage 4 of 5Next →

No leaderboard results yet.