Simone Scardapane: *Masked Siamese Networks for Label-E...| Robocrunch AI

*Masked Siamese Networks for Label-Efficient Learning*
by @mido_assran @mcaron31 @imisra_ @p_bojanowski @armandjoulin et al.

Neat new self-supervised method that combines "patch masking" with a siamese architecture and DINO-like training.https://t.co/iFiZgVhJhv pic.twitter.com/tPrEnE2YCA
— Simone Scardapane (@s_scardapane) May 2, 2022

2/7 #CVPR2022 Not all labels are created equal: https://t.co/OujNsBdB4d A look into the roles of semi-supervised learning and active learning in object detection training. @Ismail_Elezi @ZhidingYu @AnimaAnandkumar @ALVAREZ_JOSEM

Shared by Laura Leal-Taixe at 4/5/2022

Self-supervised learning techniques on images are making steady progress. Here are Masked Auto Encoders: https://t.co/eZpzogEUsZ I's impressive how much the neural network can reconstruct.

Shared by Martin Görner at 11/24/2021

Our work (\w @RisingSayak) on masked image modelling has been published in https://t.co/xurTwXlKUR. The tutorial is the paper implementation of Masked Autoencoders Are Scalable Vision Learners. arxiv: https://t.co/oXrpg3rleY Link: https://t.co/9SsLfZoHVR https://t.co/1WfR0k3suL

Shared by Aritra Roy Gosthipaty at 11/25/2021

🤗 Join your hosts @bhutanisanyam1 & @waydegilliam to learn how to train transformer models for causal and masked language modeling tasks using fastai & blurr, and talk about when it might be worth building one from scratch or fine-tuning 👉 Registration: https://t.co/kjUn17FLaK

Shared by Weights & Biases at 3/11/2022

New work with @ariG23498 on implementing Masked Autoencoders for self-supervised pretraining of images. Thanks to @endernewton for the helpful discussions.

Shared by Sayak Paul at 11/25/2021

👋Missed our AAAI'22 tutorial "Deep Learning on Graphs for Natural Language Processing"? You can now take it at your own pace. 📀Recording: https://t.co/HKdKyl84Nn 📃Slides: https://t.co/64eOrCiXmC With @lingfei_wu @chenyu_hugo @elgreco_winter @BangLiuUdeM

Shared by Yunyao Li at 2/28/2022

768