Papers with Code 아카이브

Novel Object Detection

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

하위 태스크: 0
평가표: 1
보존된 평가 기록: 5

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.

논문

이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.

Novel Object Detection

논문

MambaNeXt-YOLO: A Hybrid State Space Model for Real-time Object Detection

Language-guided Learning for Object Detection Tackling Multiple Variations in Aerial Images

MASF-YOLO: An Improved YOLOv11 Network for Small Object Detection on Drone View

An object detection approach for lane change and overtake detection from motion profiles

WoodYOLO: A Novel Object Detector for Wood Species Detection in Microscopic Images

FA-YOLO: Research On Efficient Feature Selection YOLO Improved Algorithm Based On FMDS and AGMF Modules

EMDFNet: Efficient Multi-scale and Diverse Feature Network for Traffic Sign Detection

Multi-Branch Auxiliary Fusion YOLO with Re-parameterization Heterogeneous Convolutional for accurate object detection

Mamba YOLO: A Simple Baseline for Object Detection with State Space Model

Knowledge Distillation in YOLOX-ViT for Side-Scan Sonar Object Detection

Fine-Grained Prototypes Distillation for Few-Shot Object Detection

Enhancing Novel Object Detection via Cooperative Foundational Models

Beyond the Benchmark: Detecting Diverse Anomalies in Videos

DST-Det: Simple Dynamic Self-Training for Open-Vocabulary Object Detection

Chasing Day and Night: Towards Robust and Efficient All-Day Object Detection Guided by an Event Camera

DesCo: Learning Object Recognition with Rich Language Descriptions

Meta-tuning Loss Functions and Data Augmentation for Few-shot Object Detection

PlantDet: A benchmark for Plant Detection in the Three-Rivers-Source Region

Learning to Discover and Detect Objects

PV-RCNN++: Semantical Point-Voxel Feature Interaction for 3D Object Detection

Scaling Novel Object Detection with Weakly Supervised Detection Transformers

LiDAR Cluster First and Camera Inference Later: A New Perspective Towards Autonomous Driving

Visual Understanding of Complex Table Structures from Document Images

CvT-ASSD: Convolutional vision-Transformer Based Attentive Single Shot MultiBox Detector

Partially-Supervised Novel Object Captioning Leveraging Context from Paired Data

A Unified Objective for Novel Class Discovery

SaRNet: A Dataset for Deep Learning Assisted Search and Rescue with Satellite Imagery

Instance Segmentation of Microscopic Foraminifera

Oriented Bounding Boxes for Small and Freely Rotated Objects

Unsupervised Discovery of the Long-Tail in Instance Segmentation Using Hierarchical Self-Supervision

Semantic Relation Reasoning for Shot-Stable Few-Shot Object Detection

Universal-Prototype Enhancing for Few-Shot Object Detection

Open-World Semi-Supervised Learning

Knowledge Guided Learning: Towards Open Domain Egocentric Action Recognition with Zero Supervision

CoDeNet: Efficient Deployment of Input-Adaptive Object Detection on Embedded FPGAs

Any-Shot Object Detection