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 26–50 of 53 papers

TitleStatusHype
Partially-Supervised Novel Object Captioning Leveraging Context from Paired Data—0
A Unified Objective for Novel Class DiscoveryCode1
SaRNet: A Dataset for Deep Learning Assisted Search and Rescue with Satellite ImageryCode1
Instance Segmentation of Microscopic ForaminiferaCode0
Oriented Bounding Boxes for Small and Freely Rotated Objects—0
Unsupervised Discovery of the Long-Tail in Instance Segmentation Using Hierarchical Self-Supervision—0
Semantic Relation Reasoning for Shot-Stable Few-Shot Object Detection—0
Universal-Prototype Enhancing for Few-Shot Object DetectionCode1
Open-World Semi-Supervised LearningCode1
Knowledge Guided Learning: Towards Open Domain Egocentric Action Recognition with Zero Supervision—0
CoDeNet: Efficient Deployment of Input-Adaptive Object Detection on Embedded FPGAsCode1
Any-Shot Object Detection—0
Automatic Signboard Detection and Localization in Densely Populated Developing CitiesCode0
Multi-Task Self-Supervised Object Detection via Recycling of Bounding Box Annotations—0
Learning to Detect and Retrieve Objects from Unlabeled VideosCode0
CAD-Net: A Context-Aware Detection Network for Objects in Remote Sensing ImageryCode0
ORSIm Detector: A Novel Object Detection Framework in Optical Remote Sensing Imagery Using Spatial-Frequency Channel Features—0
Grid R-CNNCode0
Deep Regionlets: Blended Representation and Deep Learning for Generic Object Detection—0
Object Detection based Deep Unsupervised Hashing—0
Deep Watershed Detector for Music Object Recognition—0
Deep Regionlets for Object Detection—0
CAD Priors for Accurate and Flexible Instance Reconstruction—0
Geometry-Based Region Proposals for Real-Time Robot Detection of Tabletop ObjectsCode0
Dictionary Pair Classifier Driven Convolutional Neural Networks for Object Detection—0
Show:102550
← PrevPage 2 of 3Next →

No leaderboard results yet.