Systems and methods for polygon object annotation and a method of training an object annotation system

A system for object annotation, comprising:

• a CNN encoder implemented by one or more computers for generating image features from a received image, the image comprising an n-dimensional array-like data structure, and the image features for predicting one or more vertexes of an object annotation;
• a recurrent decoder for generating a set of polygon predictions of an object in the received image, the recurrent decoder implemented by one or more computers;
• and
• a selector for selecting a polygon object annotation from the set of polygon predictions.

A method of annotating an object, comprising:

• receiving an image depicting an object, the image comprising an n-dimensional array-like data structure;
• generating a set of image features using a CNN encoder implemented on one or more computers;
• initializing a set of N nodes from the set of image features, the set of N nodes forming a closed curve along a circle centered in the image;
• predicting a location shift for each node simultaneously using a Graph Neural Network (GNN);
• iterating predictions through the GNN for each node, each iteration defining a new location shift for each node based on node locations for each node from the previous iteration;
• and
• producing an object annotation based on a final iteration;
• wherein the object is parametrized with one of polygons and splines.

A system for object annotation, comprising:

• a CNN encoder implemented by one or more computers for generating a set of image features from a received image, the image comprising an n-dimensional array-like data structure, and for initializing a set of N nodes from the set of image features, the set of N nodes forming a closed curve along a circle centered in the image;
• a Graph Neural Network (GNN) implemented by one or more computers for predicting a location shift for each node simultaneously and iterating predictions through the GNN for each node, each iteration defining a new location shift for each node based on node locations for each node from the previous iteration;
• and
• an output selector for producing an output based on a final iteration from the GNN.