"Self-supervised research improved greatly over the past half decade, with much of the growth being driven by objectives that are hard to quantitatively compare."
Read SPC Alumni @cinjoncin's research here
https://arxiv.org/abs/1912.00215
-
Show this thread
-
"These techniques include colorization, cyclical consistency, and noise-contrastive estimation from image patches. Consequently, the field has settled on a handful of measurements that depend on linear probes to adjudicate which approaches are the best."
1 reply 0 retweets 1 likeShow this thread -
"Our first contribution is to show that this test is insufficient and that models which perform poorly (strongly) on linear classification can perform strongly (weakly) on more involved tasks like temporal activity localization."
1 reply 0 retweets 1 likeShow this thread
"Our second contribution is to analyze the capabilities of five different representations. And our third contribution is a much needed new dataset for temporal activity localization."
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.