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 1–10 of 53 papers

TitleStatusHype
MambaNeXt-YOLO: A Hybrid State Space Model for Real-time Object Detection—0
Language-guided Learning for Object Detection Tackling Multiple Variations in Aerial Images—0
MASF-YOLO: An Improved YOLOv11 Network for Small Object Detection on Drone View—0
An object detection approach for lane change and overtake detection from motion profiles—0
Open-World Objectness Modeling Unifies Novel Object Detection—0
WoodYOLO: A Novel Object Detector for Wood Species Detection in Microscopic Images—0
FA-YOLO: Research On Efficient Feature Selection YOLO Improved Algorithm Based On FMDS and AGMF Modules—0
EMDFNet: Efficient Multi-scale and Diverse Feature Network for Traffic Sign Detection—0
Multi-Branch Auxiliary Fusion YOLO with Re-parameterization Heterogeneous Convolutional for accurate object detectionCode2
Mamba YOLO: A Simple Baseline for Object Detection with State Space ModelCode4
Show:102550
← PrevPage 1 of 6Next →

No leaderboard results yet.