Dataset driven custom learning for multi-scale object detection

A computer system for generating anchors and selecting feature maps for a multi-scale object detection program, the computer system comprising:

• one or more processors, one or more computer-readable memories, one or more computer-readable tangible storage medium, and program instructions stored on at least one of the one or more tangible storage medium for execution by at least one of the one or more processors via at least one of the one or more memories, wherein the computer system is capable of performing a method comprising:
• generating a scale distribution of one or more scales of one or more ground-truth objects;
• based on the scale distribution, dividing the effective scale range into a number of anchors greater than zero;
• generating a ratio distribution of one or more ratios of the one or more ground-truth objects;
• generating a ratio for at least one of the number of anchors;
• determining a template scale of one or more feature maps;
• and
• assigning the number of anchors to the one or more feature maps based on a relative size of a scale of one of the anchors matching a relative size of a template scale of one of the feature maps.

A computer program product for generating anchors and selecting feature maps for a multi-scale object detection program, the computer program product comprising:

• one or more computer-readable tangible storage medium and program instructions stored on at least one of the one or more tangible storage medium, the program instructions executable by a processor to cause the processor to perform a method comprising:
• generating a scale distribution of one or more scales of one or more ground-truth objects;
• based on the scale distribution, dividing the effective scale range into a number of anchors greater than zero;
• generating a ratio distribution of one or more ratios of the one or more ground-truth objects;
• generating a ratio for at least one of the number of anchors;
• determining a template scale of one or more feature maps;
• and
• assigning the number of anchors to the one or more feature maps based on a relative size of a scale of one of the anchors matching a relative size of a template scale of one of the feature maps.