AdaAttN: Revisit Attention Mechanism in Arbitrary Neural Style Transfer
— AK (@ak92501) August 10, 2021
pdf: https://t.co/VaWfcR2kKh
abs: https://t.co/FtEfKs8Ekk
github: https://t.co/Y3IFKiKZok pic.twitter.com/xO9YwDZ3cK
AdaAttN: Revisit Attention Mechanism in Arbitrary Neural Style Transfer
— AK (@ak92501) August 10, 2021
pdf: https://t.co/VaWfcR2kKh
abs: https://t.co/FtEfKs8Ekk
github: https://t.co/Y3IFKiKZok pic.twitter.com/xO9YwDZ3cK
I have no idea how I missed this. This is the most amazing thing I have seen in years! It's jupyter notebook with the scipy / pydata stack IN YOUR BROWSER!
— Andreas Mueller (@amuellerml) August 9, 2021
This literally changes everything! https://t.co/XjMaqlPvMR
Styleformer helps convert casual to formal sentences, formal to casual sentences, active to passive, and passive to active sentences.https://t.co/lzdW2XjR4c
— Daily Python Tip 🐍🐧 (@python_tip) August 7, 2021
Demo:https://t.co/EAhTKDFPfG pic.twitter.com/jjsG9Zcug2
QA Dataset Explosion: A Taxonomy of NLP Resources for Question Answering and Reading Comprehension
— Sebastian Ruder (@seb_ruder) August 6, 2021
This is an excellent overview of the QA landscape in NLP with numerous insightful observations by @annargrs @nlpmattg @IAugenstein.https://t.co/xD4Dmm886o pic.twitter.com/4oHABAPe40
Video Contrastive Learning with Global Context
— AK (@ak92501) August 6, 2021
pdf: https://t.co/0kkXi2hu3X
abs: https://t.co/se2YGoaoo6
github: https://t.co/Rhn4WJjquM pic.twitter.com/HQlA0zw2O2
I've now released a library that lets you use comments as documentation, which I call "docments".
— Jeremy Howard (@jeremyphoward) August 6, 2021
You can get it from here: https://t.co/7qOe3dwdLE pic.twitter.com/KNW9zEWEux
Token Shift Transformer for Video Classification
— AK (@ak92501) August 6, 2021
pdf: https://t.co/sdbS5P5RpD
abs: https://t.co/w5UpOnjHjl
github: https://t.co/4KQ0rdfCHN pic.twitter.com/A2RA717L84
Vision Transformer with Progressive Sampling
— AK (@ak92501) August 5, 2021
pdf: https://t.co/UW4Q8YmWPi
abs: https://t.co/usaqUHuSkS
When trained from scratch on ImageNet, PS-ViT performs 3.8% higher than the vanilla ViT in terms of top-1 accuracy with about 4× fewer parameters and 10× fewer FLOPs pic.twitter.com/ikxFIUuk9M
You only got one life. How you spend it and who you spend it with matters. This chart shows who do we spend time with across our lifetime. It's a bit crazy to see visualized just how important coworkers are. Life is too short for toxic workplaces. Source: https://t.co/oxB10hF8HM pic.twitter.com/zz6IIOE9jN
— Simon Kuestenmacher (@simongerman600) August 4, 2021
Also did you know, you can assign a bash (!) command output directly to a python variable https://t.co/6qeZjoAP4d pic.twitter.com/MiFZdjhk6g
— Jeremy Howard (@jeremyphoward) August 4, 2021
Graphic from my column puts the risk of taking the AZ vaccine in perspective. I am disappointed that so much reporting on vaccines fails to put risks into context.
— Simon Kuestenmacher (@simongerman600) August 3, 2021
My column: https://t.co/XOBTf6zJPQ
A quick video summarizing the column: https://t.co/OtZBq4C3hT pic.twitter.com/OyEs4Nv9KF
S2-MLPv2: Improved Spatial-Shift MLP Architecture for Vision
— AK (@ak92501) August 3, 2021
paper: https://t.co/SXOcXSwt5n
Using 55M parameters, S2-MLPv2-Medium achieves an 83.6% top-1 accuracy on the ImageNet-1K benchmark using 224 × 224 images without self-attention and external training data pic.twitter.com/cqTNTvcsfg