Different types of wildfires throughout the year in the US. Most wildfires caused by fireworks occur around July 4th. Source: https://t.co/ThU0ARWBY2 pic.twitter.com/ikAZjdsqn9
— Simon Kuestenmacher (@simongerman600) July 5, 2021
Different types of wildfires throughout the year in the US. Most wildfires caused by fireworks occur around July 4th. Source: https://t.co/ThU0ARWBY2 pic.twitter.com/ikAZjdsqn9
— Simon Kuestenmacher (@simongerman600) July 5, 2021
Some places where Delta is high and vaccinations are low are experiencing new surges or their worst Covid wave yet@OurWorldInData pic.twitter.com/6QlgiAjjeK
— Eric Topol (@EricTopol) July 3, 2021
Embedding-based Retrieval in Facebook Search
— ML Review (@ml_review) July 3, 2021
By @facebookai
Tricks and experiences on personalized search optimization
abs https://t.co/rFWugznMig
pdf https://t.co/xMY0CtiT4V pic.twitter.com/CHk9IOqiYY
Global Filter Networks for Image Classification
— AK (@ak92501) July 2, 2021
pdf: https://t.co/dIeGFqtllM
abs: https://t.co/48uTA872An
project page: https://t.co/LyAIupelxl
github: https://t.co/0BcTRgg4pJ pic.twitter.com/aVds2AwhCC
CSWin Transformer: A General Vision Transformer Backbone with Cross-Shaped Windows
— AK (@ak92501) July 2, 2021
pdf: https://t.co/6KuG5MRGPM
85.4% Top-1 accuracy on ImageNet-1K without any extra training data or label, 53.9 box AP and 46.4 mask AP on the COCO detection task pic.twitter.com/pHZdSI0RBa
Focal Self-attention for Local-Global Interactions in
— AK (@ak92501) July 2, 2021
Vision Transformers
pdf: https://t.co/2mFN1OQzVG
largest Focal Transformer yields 58.7/58.9 box mAPs and 50.9/51.3 mask mAPs on COCO mini-val/test-dev, and 55.4 mIoU on ADE20K for semantic segmentation pic.twitter.com/ij7VYIbcQR
AutoFormer: Searching Transformers for Visual Recognition
— AK (@ak92501) July 2, 2021
pdf: https://t.co/BfcLzNpd2I
abs: https://t.co/pFSpFDrBOZ
github: https://t.co/SBeDmRhmET
AutoFormer-tiny/small/base achieve 74.7%/81.7%/82.4% top-1 accuracy on ImageNet with 5.7M/22.9M/53.7M parameters, respectively pic.twitter.com/kC8DykvoiM
RLCard - A Toolkit for Reinforcement Learning in Card Games. https://t.co/UB6RGcCVdS #Python #CardGames pic.twitter.com/SHj50MJWob
— Python Weekly (@PythonWeekly) July 1, 2021
Augmented Shortcuts for Vision Transformers
— AK (@ak92501) July 1, 2021
pdf: https://t.co/68X2iVPoQd
abs: https://t.co/bo2BI1Suoe
brings about 1% accuracy increase of the sota visual transformers without obviously increasing their parameters and FLOPs pic.twitter.com/UnaaJKvIUv
SCARF: Self-Supervised Contrastive Learning using Random Feature Corruption
— AK (@ak92501) June 30, 2021
pdf: https://t.co/YmfyNkLcC9
abs: https://t.co/m4kiQq0j5Q
technique for contrastive learning, where views are formed by corrupting a random subset of features pic.twitter.com/pP6phV9p3m
Francesca Tripodi just published an amazing paper on how Wikipedia articles about women are more frequently mis-categorized as "not notable" and the additional labor it takes to combat this. You should read the paper, but here are some highlights: pic.twitter.com/fUky0b9kn8
— Amelia McNamara (@AmeliaMN) June 29, 2021
✨💖 Ecstatic to *finally* be able to talk about Copilot: a collaboration between @Github, @OpenAI, and @Microsoft's Developer Tools division.
— 👩💻 Paige Bailey #BlackLivesMatter (@DynamicWebPaige) June 29, 2021
I've been using it for everything from FORTRAN to Markdown to Python for the last months, and it has made me *so much more* productive. https://t.co/Zy3IgfBawd