System, method and computer program product for generating a training set for a classifier

A non-transitory computer readable storage medium comprising instructions, which when executed by a processor, cause the processor to:

• review at least part of potential defects of an examined object, and assign each of the at least part of the potential defects with a multiplicity of attribute values;
• and
• classify, based on the attribute values as assigned, the at least part of potential defects into a set of classes, the set comprising at least a first major class, a second major class and a first minor class, wherein the processor is to classify the at least part of potential defects using a classifier trained based on a training set that comprises a multiplicity of training defects with assigned attribute values, the training defects classified into the set of classes.

A method comprising:

• reviewing at least part of potential defects of an examined object, and assigning each of the at least part of the potential defects with a multiplicity of attribute values;
• and
• classifying, based on the attribute values as assigned, the at least part of potential defects into a set of classes, the set comprising at least a first major class, a second major class and a first minor class, wherein the at least part of potential defects is classified using a classifier trained based on a training set that comprises a multiplicity of training defects with assigned attribute values, the training defects classified into the set of classes.