Intriguing measure of #bias in #DeepLearning We find angular distance as a robust + universal measure of hardness of a training example and corresponds with human ambiguity. @beidichen @animesh_garg @jankautz
@NvidiaAIhttps://twitter.com/Deep__AI/status/1203028047651205120 …
-
Show this thread
-
For a talk describing this paper, watch my
#GTC talkhttps://on-demand.gputechconf.com/gtcdc/2019/video/dc91298-tackling-data-scarcity-and-bias-in-deep-learning/ …1 reply 6 retweets 20 likesShow this thread -
Main slides from the talk. Loss in
#DeepLearning made of norm+angular improvement. Angles are better matched for easier examples. Angles are also better when there is better generalization.pic.twitter.com/c9hm2G7DNw
1 reply 8 retweets 42 likesShow this thread -
We use human selection frequency annotations collected by
@beenwrekt on Imagenet to validate our findings1 reply 2 retweets 7 likesShow this thread
And thanks to @Anshumali_ for collaborating with @NvidiaAI on this project. He was tagged in the original tweet, but got dropped after that. Sorry about that!
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.