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

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–10 of 57 papers

TitleStatusHype
VisionReasoner: Unified Visual Perception and Reasoning via Reinforcement LearningCode4
Towards a Multi-Agent Vision-Language System for Zero-Shot Novel Hazardous Object Detection for Autonomous Driving SafetyCode0
Finding the Reflection Point: Unpadding Images to Remove Data Augmentation Artifacts in Large Open Source Image Datasets for Machine Learning—0
The Power of One: A Single Example is All it Takes for Segmentation in VLMs—0
LangGas: Introducing Language in Selective Zero-Shot Background Subtraction for Semi-Transparent Gas Leak Detection with a New DatasetCode1
UniFa: A unified feature hallucination framework for any-shot object detection—0
CP-DETR: Concept Prompt Guide DETR Toward Stronger Universal Object Detection—0
No Annotations for Object Detection in Art through Stable DiffusionCode0
Gaussian Splatting Under Attack: Investigating Adversarial Noise in 3D ObjectsCode0
DINO-X: A Unified Vision Model for Open-World Object Detection and UnderstandingCode5
Show:102550
← PrevPage 1 of 6Next →

No leaderboard results yet.