About

Real-time object detection is the task of doing object detection in real-time with fast inference while maintaining a base level of accuracy.

( Image credit: CenterNet )

Benchmarks

TREND DATASET BEST METHOD PAPER TITLE PAPER CODE COMPARE

Greatest papers with code

SpineNet: Learning Scale-Permuted Backbone for Recognition and Localization

CVPR 2020 tensorflow/models

We propose SpineNet, a backbone with scale-permuted intermediate features and cross-scale connections that is learned on an object detection task by Neural Architecture Search.

IMAGE CLASSIFICATION INSTANCE SEGMENTATION NEURAL ARCHITECTURE SEARCH REAL-TIME OBJECT DETECTION

EfficientDet: Scalable and Efficient Object Detection

CVPR 2020 tensorflow/models

Model efficiency has become increasingly important in computer vision.

 Ranked #1 on Object Detection on COCO minival (AP50 metric)

AUTOML REAL-TIME OBJECT DETECTION

Objects as Points

16 Apr 2019tensorflow/models

We model an object as a single point --- the center point of its bounding box.

Ranked #13 on Real-Time Object Detection on COCO (using extra training data)

KEYPOINT DETECTION REAL-TIME OBJECT DETECTION

Focal Loss for Dense Object Detection

ICCV 2017 tensorflow/models

Our novel Focal Loss focuses training on a sparse set of hard examples and prevents the vast number of easy negatives from overwhelming the detector during training.

DENSE OBJECT DETECTION REAL-TIME OBJECT DETECTION REGION PROPOSAL

R-FCN: Object Detection via Region-based Fully Convolutional Networks

NeurIPS 2016 facebookresearch/detectron

In contrast to previous region-based detectors such as Fast/Faster R-CNN that apply a costly per-region subnetwork hundreds of times, our region-based detector is fully convolutional with almost all computation shared on the entire image.

REAL-TIME OBJECT DETECTION

Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks

NeurIPS 2015 facebookresearch/detectron

In this work, we introduce a Region Proposal Network (RPN) that shares full-image convolutional features with the detection network, thus enabling nearly cost-free region proposals.

REAL-TIME OBJECT DETECTION REGION PROPOSAL

YOLOv4: Optimal Speed and Accuracy of Object Detection

23 Apr 2020pjreddie/darknet

There are a huge number of features which are said to improve Convolutional Neural Network (CNN) accuracy.

 Ranked #1 on Object Detection on CrowdHuman (full body) (AP 0.5 metric)

DATA AUGMENTATION REAL-TIME OBJECT DETECTION

Scaled-YOLOv4: Scaling Cross Stage Partial Network

16 Nov 2020AlexeyAB/darknet

We show that the YOLOv4 object detection neural network based on the CSP approach, scales both up and down and is applicable to small and large networks while maintaining optimal speed and accuracy.

REAL-TIME OBJECT DETECTION