5,337
edits
Visual Learning and Recognition: Difference between revisions
Visual Learning and Recognition (view source)
Revision as of 17:31, 10 September 2020
, 10 September 2020→Data-driven Methods in Vision
| Line 23: | Line 23: | ||
;Rule of thumb: | ;Rule of thumb: | ||
(Simple algorithms + big data) is better than (complicated algorithms + small data) | (Simple algorithms + big data) is better than (complicated algorithms + small data) | ||
== | |||
Lecture 4 (September 10, 2020) | ===Lecture 4 (September 10, 2020)=== | ||
This lecture is on the bias of data. It follows Torralba ''et al.''<ref name="torralba2011unbiased"></ref> | This lecture is on the bias of data. It follows Torralba ''et al.''<ref name="torralba2011unbiased"></ref> | ||
| Line 46: | Line 46: | ||
* Social Bias | * Social Bias | ||
Graduation photos always have a certain structure. | Graduation photos always have a certain structure. | ||
===Measuring Dataset Bias=== | |||
Evaluate cross-dataset performance | |||
==Data-driven Methods in Vision== | |||
==Will be on the exam== | ==Will be on the exam== | ||