Characterizing a classification difficulty associated with a target data item

A system for identifying potentially mislabeled data samples, the system comprising:

• a processor configured to:
• receive a dataset comprising a plurality of data items, wherein at least a portion of the plurality of data items is each associated with a corresponding class label from labels of a plurality of classes;
• for each class of the plurality of classes, train a separate class-conditional reconstructor on one or more of the data items associated with that class;
• and
• for a target data item in the dataset having a target class label among the labels of the plurality of classes:
• calculate a first reconstruction error using a class-conditional reconstructor trained for the target class label;
• calculate a second reconstruction error using a class-conditional reconstructor trained for a class other than the target class label;
• determine a ratio of the first reconstruction error to the second reconstruction error;
• and
• using the ratio, characterize a classification associated with the target data item;
• and
• a memory coupled to the processor and configured to provide the processor with instructions.

A computer program product embodied in a non-transitory computer readable medium and comprising computer instructions for:

• receiving a dataset comprising a plurality of data items, wherein at least a portion of the plurality of data items is each associated with a corresponding class label from labels of a plurality of classes;
• for each class of the plurality of classes, training a separate class-conditional reconstructor on one or more of the data items associated with that class;
• and
• for a target data item in the dataset having a target class label among the labels of the plurality of classes:
• calculating a first reconstruction error using a class-conditional reconstructor trained for the target class label;
• calculating a second reconstruction error using a class-conditional reconstructor trained for a class other than the target class label;
• determining a ratio of the first reconstruction error to the second reconstruction error;
• and
• using the ratio, characterizing a classification associated with the target data item.