Object Detection
3727 papers with code • 91 benchmarks • 263 datasets
Object Detection is a computer vision task in which the goal is to detect and locate objects of interest in an image or video. The task involves identifying the position and boundaries of objects in an image, and classifying the objects into different categories. It forms a crucial part of vision recognition, alongside image classification and retrieval.
The state-of-the-art methods can be categorized into two main types: one-stage methods and two stage-methods:
-
One-stage methods prioritize inference speed, and example models include YOLO, SSD and RetinaNet.
-
Two-stage methods prioritize detection accuracy, and example models include Faster R-CNN, Mask R-CNN and Cascade R-CNN.
The most popular benchmark is the MSCOCO dataset. Models are typically evaluated according to a Mean Average Precision metric.
( Image credit: Detectron )
Libraries
Use these libraries to find Object Detection models and implementationsDatasets
Subtasks
- 3D Object Detection
- Real-Time Object Detection
- RGB Salient Object Detection
- Few-Shot Object Detection
- Few-Shot Object Detection
- Video Object Detection
- RGB-D Salient Object Detection
- Open Vocabulary Object Detection
- Object Detection In Aerial Images
- Weakly Supervised Object Detection
- Robust Object Detection
- Small Object Detection
- Medical Object Detection
- Zero-Shot Object Detection
- Open World Object Detection
- Co-Salient Object Detection
- Dense Object Detection
- Object Proposal Generation
- Video Salient Object Detection
- Camouflaged Object Segmentation
- License Plate Detection
- Head Detection
- Multiview Detection
- 3D Object Detection From Monocular Images
- One-Shot Object Detection
- Moving Object Detection
- Surgical tool detection
- Described Object Detection
- Body Detection
- Pupil Detection
- Object Detection In Indoor Scenes
- Class-agnostic Object Detection
- Semantic Part Detection
- Object Skeleton Detection
- Fish Detection
- Multiple Affordance Detection
- Weakly Supervised 3D Detection
Latest papers
Generating Minimalist Adversarial Perturbations to Test Object-Detection Models: An Adaptive Multi-Metric Evolutionary Search Approach
Deep Learning (DL) models excel in computer vision tasks but can be susceptible to adversarial examples.
Vision Transformer-based Adversarial Domain Adaptation
Unsupervised domain adaptation (UDA) aims to transfer knowledge from a labeled source domain to an unlabeled target domain.
Revisiting Out-of-Distribution Detection in LiDAR-based 3D Object Detection
LiDAR-based 3D object detection has become an essential part of automated driving due to its ability to localize and classify objects precisely in 3D.
Unified Unsupervised Salient Object Detection via Knowledge Transfer
Firstly, we propose a Progressive Curriculum Learning-based Saliency Distilling (PCL-SD) mechanism to extract saliency cues from a pre-trained deep network.
Efficient and Concise Explanations for Object Detection with Gaussian-Class Activation Mapping Explainer
To address the challenges of providing quick and plausible explanations in Explainable AI (XAI) for object detection models, we introduce the Gaussian Class Activation Mapping Explainer (G-CAME).
The devil is in the object boundary: towards annotation-free instance segmentation using Foundation Models
Foundation models, pre-trained on a large amount of data have demonstrated impressive zero-shot capabilities in various downstream tasks.
Multi-resolution Rescored ByteTrack for Video Object Detection on Ultra-low-power Embedded Systems
This paper introduces Multi-Resolution Rescored Byte-Track (MR2-ByteTrack), a novel video object detection framework for ultra-low-power embedded processors.
Learning Feature Inversion for Multi-class Anomaly Detection under General-purpose COCO-AD Benchmark
Moreover, current metrics such as AU-ROC have nearly reached saturation on simple datasets, which prevents a comprehensive evaluation of different methods.
Low-Light Image Enhancement Framework for Improved Object Detection in Fisheye Lens Datasets
This study addresses the evolving challenges in urban traffic monitoring detection systems based on fisheye lens cameras by proposing a framework that improves the efficacy and accuracy of these systems.
Training-free Boost for Open-Vocabulary Object Detection with Confidence Aggregation
Specifically, in the region-proposal stage, proposals that contain novel instances showcase lower objectness scores, since they are treated as background proposals during the training phase.