2nd talk I've seen on failures of deep captioning & VQA models that got defensive replies, e.g. "Have you tried lowering the learning rate?"
Replying to @iskander
but did they try adding more layers?
12:38 PM - 7 Aug 2016
0 replies
0 retweets
2 likes
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.