I want to do Object Detection and Segmentation. I want to find out which models are trained on COCO-Dataset eg YOLO etc. But I want to find out which model has the highest accuracy and lowest time. In short which model is best for object detection and segmentation which are trained on COCO -dataset
-
$\begingroup$ Do let me know if you are satisfied with the answer? If not I will try my best possible way to edit it. Please consider accepting the answer if it answers your question. $\endgroup$– Devashish PrasadJun 3, 2021 at 15:14
1 Answer
I want to find out that which models are trained on COCO-Dataset
Here you can find state of the art models for instance segmentation on COCO dataset. And here you can find state of the art models for object detection. You will also find open sourced code and models for most of them.
But I want to find out that which model has highest accuracy and lowest time.
Here you can find state of the art models for real time object detection. You can refer the FPS metric mentioned in the table to compare their speeds. Following is the image from current table topper (as of 31st May 2021).
Here you can find state of the art models for real time instance segmentation. Again you can refer the FPS metric mentioned in the table to compare their speeds. SipMask++ is the current table topper (as of 31st May 2021).
I want to do Object detection and Segmentation.
If you have instance segmentation mask of an object, then you can easily get the bouding box out if it.
-
$\begingroup$ I want that which object detection models are trained on COCO dataset and what are their pros and cons in terms of speed and accuracy $\endgroup$– HamzaMay 31, 2021 at 10:23
-