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 )
|TREND||DATASET||BEST METHOD||PAPER TITLE||PAPER||CODE||COMPARE|
Plugged into the FCOS object detector, the SAG-Mask branch predicts a segmentation mask on each box with the spatial attention map that helps to focus on informative pixels and suppress noise.
We propose a Harmonic Densely Connected Network to achieve high efficiency in terms of both low MACs and memory traffic.
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
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.
We introduce a novel and generic convolutional unit, DiCE unit, that is built using dimension-wise convolutions and dimension-wise fusion.
#21 best model for Object Detection on PASCAL VOC 2007
As DenseNet conserves intermediate features with diverse receptive fields by aggregating them with dense connection, it shows good performance on the object detection task.
Together these two variants address the two critical use cases in efficient object detection: improving efficiency without sacrificing accuracy, and improving accuracy at real-time efficiency.
#8 best model for Real-Time Object Detection on COCO
Here we aim to learn a better architecture of feature pyramid network for object detection.
#11 best model for Real-Time Object Detection on COCO (MAP metric)
In this study, we propose an efficient architecture named PeleeNet, which is built with conventional convolution instead.