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 21–30 of 53 papers

TitleStatusHype
Deep Regionlets for Object Detection—0
Deep Watershed Detector for Music Object Recognition—0
Dictionary Pair Classifier Driven Convolutional Neural Networks for Object Detection—0
EMDFNet: Efficient Multi-scale and Diverse Feature Network for Traffic Sign Detection—0
FA-YOLO: Research On Efficient Feature Selection YOLO Improved Algorithm Based On FMDS and AGMF Modules—0
Knowledge Guided Learning: Towards Open Domain Egocentric Action Recognition with Zero Supervision—0
Language-guided Learning for Object Detection Tackling Multiple Variations in Aerial Images—0
ORSIm Detector: A Novel Object Detection Framework in Optical Remote Sensing Imagery Using Spatial-Frequency Channel Features—0
Partially-Supervised Novel Object Captioning Leveraging Context from Paired Data—0
PlantDet: A benchmark for Plant Detection in the Three-Rivers-Source Region—0
Show:102550
← PrevPage 3 of 6Next →

No leaderboard results yet.