5,337
edits
Visual Learning and Recognition: Difference between revisions
Visual Learning and Recognition (view source)
Revision as of 14:27, 11 September 2020
, 11 September 2020→Measuring Dataset Bias
| Line 50: | Line 50: | ||
Evaluate cross-dataset performance | Evaluate cross-dataset performance | ||
Train on one dataset, test on another | Train on one dataset, test on another | ||
To evaluate negative set bias, pool negatives from other datasets (e.g. not car or not person). | |||
They found that models trained on a dataset do ~8% worse at detecting negatives from other datasets. | |||
===Overcoming Datset Bias=== | ===Overcoming Datset Bias=== | ||