Difference between revisions of "Sketchy recognition 2020"

From DiVersions
Jump to navigation Jump to search
(Title)
(Sketchy Recognition)
Line 3: Line 3:
 
=== Addressing the model ===
 
=== Addressing the model ===
  
 +
[[File:Diversions_post_pianofabriek_scanned_drawings.screen.pdf|page=33|thumb]]
 
[[File:Diversions_post_pianofabriek_scanned_drawings.screen.pdf|page=36|thumb]]
 
[[File:Diversions_post_pianofabriek_scanned_drawings.screen.pdf|page=36|thumb]]
 
[[File:Diversions_post_pianofabriek_scanned_drawings.screen.pdf|page=30|thumb]]
 
[[File:Diversions_post_pianofabriek_scanned_drawings.screen.pdf|page=30|thumb]]
  
In one instance, the drawer replied to the systems interpretation of her drawing as a "skyscraper", by  having her drawn figure announce, "I am a skyscraper on the inside". At one point another participants responded to the interpretation of her drawing in progress as possibly a "fire-hydrant" by directly addressing the model writing on her drawing "you are US-centric".
+
In some cases, drawers could be seen to follow the intepretations given by the computer vision model. In one instance, the (mis) intepretation of her drawing of a bear as a cactus, led the drawer to add spikes in response. In another case, the drawer replied to the systems interpretation of her drawing as a "skyscraper", by  having her drawn figure announce, "I am a skyscraper on the inside". Some reponses were more confrontational, as the drawer (in this case someone familiar with machine learning models) responded to the interpretation of her drawing in progress as possibly a "fire-hydrant" by directly addressing the model writing on her drawing "you are US-centric".
 +
 
  
 
=== Subsection ===
 
=== Subsection ===

Revision as of 08:11, 15 May 2020

Sketchy Recognition

Addressing the model

Diversions post pianofabriek scanned drawings.screen.pdf
Diversions post pianofabriek scanned drawings.screen.pdf
Diversions post pianofabriek scanned drawings.screen.pdf

In some cases, drawers could be seen to follow the intepretations given by the computer vision model. In one instance, the (mis) intepretation of her drawing of a bear as a cactus, led the drawer to add spikes in response. In another case, the drawer replied to the systems interpretation of her drawing as a "skyscraper", by having her drawn figure announce, "I am a skyscraper on the inside". Some reponses were more confrontational, as the drawer (in this case someone familiar with machine learning models) responded to the interpretation of her drawing in progress as possibly a "fire-hydrant" by directly addressing the model writing on her drawing "you are US-centric".


Subsection