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 1–25 of 53 papers

TitleStatusHype
Mamba YOLO: A Simple Baseline for Object Detection with State Space ModelCode4
Knowledge Distillation in YOLOX-ViT for Side-Scan Sonar Object DetectionCode2
Multi-Branch Auxiliary Fusion YOLO with Re-parameterization Heterogeneous Convolutional for accurate object detectionCode2
Fine-Grained Prototypes Distillation for Few-Shot Object DetectionCode2
Scaling Novel Object Detection with Weakly Supervised Detection TransformersCode1
Enhancing Novel Object Detection via Cooperative Foundational ModelsCode1
DST-Det: Simple Dynamic Self-Training for Open-Vocabulary Object DetectionCode1
CoDeNet: Efficient Deployment of Input-Adaptive Object Detection on Embedded FPGAsCode1
Open-World Semi-Supervised LearningCode1
Universal-Prototype Enhancing for Few-Shot Object DetectionCode1
Chasing Day and Night: Towards Robust and Efficient All-Day Object Detection Guided by an Event CameraCode1
A Unified Objective for Novel Class DiscoveryCode1
Learning to Discover and Detect ObjectsCode1
DesCo: Learning Object Recognition with Rich Language DescriptionsCode1
SaRNet: A Dataset for Deep Learning Assisted Search and Rescue with Satellite ImageryCode1
CAD-Net: A Context-Aware Detection Network for Objects in Remote Sensing ImageryCode0
Learning to Detect and Retrieve Objects from Unlabeled VideosCode0
Instance Segmentation of Microscopic ForaminiferaCode0
Beyond the Benchmark: Detecting Diverse Anomalies in VideosCode0
T-CNN: Tubelets with Convolutional Neural Networks for Object Detection from VideosCode0
Grid R-CNNCode0
Geometry-Based Region Proposals for Real-Time Robot Detection of Tabletop ObjectsCode0
CvT-ASSD: Convolutional vision-Transformer Based Attentive Single Shot MultiBox DetectorCode0
Automatic Signboard Detection and Localization in Densely Populated Developing CitiesCode0
Deep Watershed Detector for Music Object Recognition—0
Show:102550
← PrevPage 1 of 3Next →

No leaderboard results yet.