SOTAVerified

Novel Object Detection

Novel Object Detection is a challenging task introduced by Fomenko et.al. in their paper "Learning to Discover and Detect Objects". The goal in this task is to measure mAP performance on known as well as novel classes, where the known classes correspond to the 80 COCO classes, and the novel classes are the remaining 1123 classes from LVIS dataset. Thus, during training the model can only be trained with annotations from COCO dataset, but during evaluation/inference it is expected to BOTH classify and detect objects belonging to ALL the classes in the LVIS dataset.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 41–50 of 53 papers

TitleStatusHype
Language-guided Learning for Object Detection Tackling Multiple Variations in Aerial Images—0
LiDAR Cluster First and Camera Inference Later: A New Perspective Towards Autonomous Driving—0
MambaNeXt-YOLO: A Hybrid State Space Model for Real-time Object Detection—0
MASF-YOLO: An Improved YOLOv11 Network for Small Object Detection on Drone View—0
Meta-tuning Loss Functions and Data Augmentation for Few-shot Object Detection—0
Multi-Task Self-Supervised Object Detection via Recycling of Bounding Box Annotations—0
Object Detection based Deep Unsupervised Hashing—0
Open-World Objectness Modeling Unifies Novel Object Detection—0
Oriented Bounding Boxes for Small and Freely Rotated Objects—0
ORSIm Detector: A Novel Object Detection Framework in Optical Remote Sensing Imagery Using Spatial-Frequency Channel Features—0
Show:102550
← PrevPage 5 of 6Next →

No leaderboard results yet.