Ross Wightman    @wightmanr    11/25/2021      

Has anyone out there done some extensive experiments with normalization layers outside the usual suspects (BN, GN, LN, IN) on image tasks w/ large(ish) natural image datasets (ImageNet, COCO, or >, etc) and found some good setups that they're not sharing with the rest of us?
    3         53


Simone Scardapane    @s_scardapane    10/5/2021      

*On the genealogy of ML datasets: A critical history of ImageNet* by @cephaloponderer @alexhanna @amironesei @andrewthesmart Nicole Intriguing article exploring some norms & values implicit in datasets such as ImageNet, and the outsized influence they end up having in ML. 1/x

AK    @ak92501    4 hours      

AdaViT: Adaptive Vision Transformers for Efficient Image Recognition abs: experiments on ImageNet, method obtains more than 2× improvement on efficiency compared to sota vision transformers with 0.8% drop of accuracy
    9         23

AK    @ak92501    11/29/2021      

SwinBERT: End-to-End Transformers with Sparse Attention for Video Captioning abs: experiments on 5 video captioning datasets, show that SWINBERT achieves across-the-board performance improvements over previous methods
    2         7

Thomas Wolf    @Thom_Wolf    8/19/2021      

A few years ago I was mostly interested in models, creating 🤗transformers, adding BERT, GPT, T5… Over time I’ve seen my interests shift to data (sharing, evaluation, processing) leading to 🤗datasets And I see many people around me follow a similar path We are slowly maturing
    65         420