DETReg: Unsupervised Pretraining with Region Priors for Object Detection
— AK (@ak92501) June 9, 2021
pdf: https://t.co/rLPSu27w7A
abs: https://t.co/9aaGSJeeqB
project page: https://t.co/mnCDiWBftJ
unsupervised pretraining approach for object detection with transformers using region priors pic.twitter.com/lTH36cBcvk
Motor vehicle death rates skyrocketed in 2020 - about 25-30% higher since March
— Teddy Petrou (@TedPetrou) June 9, 2021
Overall deaths inc substantially too. The death rate inc more than miles driven decreased
Death rates have not been this high since the mid 90s. Going back to normal saves 1000s of lives on the road pic.twitter.com/8LuAs01ngW
Self-Damaging Contrastive Learning
— AK (@ak92501) June 8, 2021
pdf: https://t.co/wHoD6UJVoT
abs: https://t.co/cBy0btgmR0
github: https://t.co/AzLq4utoiX pic.twitter.com/DnutaOKrje
Today's paper is Why Stress Is Bad for Your Brain.
— Fermat's Library (@fermatslibrary) June 8, 2021
Our bodies' stress response evolved to help us get out of short-term physical emergencies. Such reactions compromise long-term physical health in favor of immediate self-preservation.
Read on: https://t.co/oaV1SOL7Z7 pic.twitter.com/hJ3V3asmlf
I'm regularly shocked by folks who think building some crappy app on top of their data is superior to just giving a link to a zipped csv of the freaking data. https://t.co/kPnOVQyvbV
— JD Long (@CMastication) June 8, 2021
Shuffle Transformer: Rethinking Spatial Shuffle for
— AK (@ak92501) June 8, 2021
Vision Transformer
pdf: https://t.co/qkqHXKWpLu
abs: https://t.co/VpAssMY0Ec pic.twitter.com/JQYVlUPeoO
Uformer: A General U-Shaped Transformer for Image Restoration
— AK (@ak92501) June 8, 2021
pdf: https://t.co/VHxgIBI0yr
abs: https://t.co/xqHomTEIzQ
achieves sota performance on several tasks, including denoising, deraining, deblurring, and demoireing pic.twitter.com/1JC2rSIMsx
Solving problems with ML ✅
— TensorFlow (@TensorFlow) June 7, 2021
Get to know common machine learning use cases like analyzing multimedia, building smart search, and transforming data, and learn how to quickly build them into your app to help solve everyday problems.
Check it out → https://t.co/yEph3dGyQv pic.twitter.com/mJmpBRfz4A
Your periodic reminder that @JennyBryan has collected a bunch of resources for free, open licensed images you can use for talks: https://t.co/IqCAmX9KvX
— Amelia McNamara (@AmeliaMN) June 7, 2021
gghighlight 0.3.2 is on CRAN now!🎉 I wrote a quick blog post to explain two new features, including the one used in the this 📈. #rstats
— Hiroaki Yutani (@yutannihilat_en) June 7, 2021
Wannabe Rstats-fu: gghighlight 0.3.2https://t.co/tFpR55jH6M pic.twitter.com/qoQ4neENwp
Self-Attention Between Datapoints: Going Beyond Individual Input-Output Pairs in Deep Learning
— AK (@ak92501) June 7, 2021
pdf: https://t.co/vvC4sfE9i3
abs: https://t.co/mxlAWuAyiY
architecture that takes the entire dataset as input and uses self-attention to model complex relationships
between datapoints pic.twitter.com/5PQmSRDxwe
A "steep learning curve" is the best kind of learning curve: it means you're learning fast.
— Tim Harford (@TimHarford) June 6, 2021
And when what you're learning to do is make things such as batteries, you get the kind of invention that quietly revolutionises the world.https://t.co/mWgm7FVQW2 pic.twitter.com/WD0HndAQzr
