Real-time object detection is the task of doing object detection in real-time with fast inference while maintaining a base level of accuracy.
|Trend||Dataset||Best Method||Paper title||Paper||Code||Compare|
Compared to YOLOv2 on the MS-COCO object detection, ESPNetv2 delivers 4. 4% higher accuracy with 6x fewer FLOPs.
#19 best model for Object Detection on PASCAL VOC 2007
In this study, we propose an efficient architecture named PeleeNet, which is built with conventional convolution instead.
In addition to requiring high accuracy to ensure safety, object detection for autonomous driving also requires real-time inference speed to guarantee prompt vehicle control, as well as small model size and energy efficiency to enable embedded system deployment.
In object detection, reducing computational cost is as important as improving accuracy for most practical usages.
Drones or general Unmanned Aerial Vehicles (UAVs), endowed with computer vision function by on-board cameras and embedded systems, have become popular in a wide range of applications.
A unified deep neural network, denoted the multi-scale CNN (MS-CNN), is proposed for fast multi-scale object detection.
#10 best model for Face Detection on WIDER Face (Hard)
Real-time scene understanding has become crucial in many applications such as autonomous driving.
#3 best model for Real-Time Object Detection on PASCAL VOC 2007
Our model shows significant improvements over state-of-the-art models across various visual recognition tasks, including image classification, object detection, and semantic segmentation.
#20 best model for Object Detection on PASCAL VOC 2007
Experiments on MS COCO show that our TTFNet has great advantages in balancing training time, inference speed, and accuracy.
#2 best model for Real-Time Object Detection on COCO
Subsequently we identify a sparse distribution estimation scheme, Directed Sparse Sampling, and employ it in a single end-to-end CNN based detection model.
#10 best model for Object Detection on PASCAL VOC 2007