5,337
edits
Visual Learning and Recognition: Difference between revisions
Visual Learning and Recognition (view source)
Revision as of 17:28, 10 September 2020
, 10 September 2020→Data-driven Methods in Vision
No edit summary |
|||
| Line 24: | Line 24: | ||
(Simple algorithms + big data) is better than (complicated algorithms + small data) | (Simple algorithms + big data) is better than (complicated algorithms + small data) | ||
==Data-driven Methods in Vision== | ==Data-driven Methods in Vision== | ||
Lecture 4 (September 10, 2020) | |||
This lecture is on the bias of data. It follows Torralba ''et al.''<ref name="torralba2011unbiased"></ref> | |||
;Will big data solve all our problems? | |||
E.g. Can (big company) just dump millions of dollars to collect data and solve any problem? | |||
No. E.g. COVID. | |||
There will always be new tasks or problems. | |||
===We will never have enough data=== | |||
Long tails - Zipf's law | |||
===Data is biased=== | |||
Types of visual bias: | |||
* Observer Bias (human vs bird) | |||
* Capture Bias (photographer vs robot) | |||
* Selection Bias (Flickr vs Google Street View) | |||
* Category/Label Bias | |||
* Negative Set Bias | |||
In general, all datasets will have all of these biases mixed in. | |||
* Social Bias | |||
Graduation photos always have a certain structure. | |||
==Will be on the exam== | ==Will be on the exam== | ||