SOTAVerified

Zero-Shot Object Detection

Zero-shot object detection (ZSD) is the task of object detection where no visual training data is available for some of the target object classes.

( Image credit: Zero-Shot Object Detection: Learning to Simultaneously Recognize and Localize Novel Concepts )

Papers

Showing 110 of 57 papers

TitleStatusHype
YOLO-World: Real-Time Open-Vocabulary Object DetectionCode9
Grounding DINO 1.5: Advance the "Edge" of Open-Set Object DetectionCode7
T-Rex2: Towards Generic Object Detection via Text-Visual Prompt SynergyCode7
DINO-X: A Unified Vision Model for Open-World Object Detection and UnderstandingCode5
Real-time Transformer-based Open-Vocabulary Detection with Efficient Fusion HeadCode5
Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object DetectionCode5
VisionReasoner: Unified Visual Perception and Reasoning via Reinforcement LearningCode4
ELEVATER: A Benchmark and Toolkit for Evaluating Language-Augmented Visual ModelsCode4
OV-DINO: Unified Open-Vocabulary Detection with Language-Aware Selective FusionCode3
Multi-modal Queried Object Detection in the WildCode2
Show:102550
← PrevPage 1 of 6Next →

No leaderboard results yet.