What are these? 🌉🗽
— TensorFlow (@TensorFlow) October 28, 2020
#TFHub can help you classify famous sights with a great set of landmark detection models readily available for every continent.
Model collection → https://t.co/4c8WkMiT8N pic.twitter.com/mqOij6zBKW
Visual Transformer with pre-trained weights, now available thanks to the fantastic @wightmanr https://t.co/mwqylvyBnm
— PyTorch (@PyTorch) October 28, 2020
Want to learn representations that generalise in a self-supervised way? Our researchers propose ReLIC to show how to leverage causality to learn robust representations: https://t.co/HOUJtTMzg6
— DeepMind (@DeepMind) October 23, 2020
Work by @jovana_mitr, Brian McWilliams, Jacob Walker, Lars Buesing, @blundellcharles. pic.twitter.com/wSumvnQdKw
The level of complexity of this autonomous car reminded me of ALVINN: an autonomous land vehicle in a neural network, developed by Dean Pomerleau in the early 1990s.https://t.co/NHdNODWpAT https://t.co/nQZsU7N55O pic.twitter.com/A6p7Z9CtDQ
— hardmaru (@hardmaru) October 16, 2020
Are all negatives created equal in contrastive instance discrimination?
— Ari Morcos (@arimorcos) October 15, 2020
In new work led by Tiffany Cai, we show that only the hardest 5% of negatives per query are both necessary and largely sufficient for self-supervised learning.
Tweetprint time!https://t.co/ijyrMb4zGG pic.twitter.com/dIeR7DptVF
Very Deep VAEs Generalize Autoregressive Models and Can Outperform Them on Images
— hardmaru (@hardmaru) October 6, 2020
“Very Deep VAEs” achieve higher likelihoods, use fewer parameters, generate samples 1000x faster, and are more easily applied to hi-res images, compared to PixelCNN.https://t.co/bjjKrZvnb2 pic.twitter.com/u1xMHJiRpp
VQ-VAE + Transformer look much better than VAE + LSTMhttps://t.co/TBfxy3jysl https://t.co/NCfTl0eps5
— hardmaru (@hardmaru) October 3, 2020
Image GANs meet Differentiable Rendering for Inverse Graphics and Interpretable 3D Neural Rendering
— AK (@ak92501) October 3, 2020
pdf: https://t.co/xP5VjzSOR5
abs: https://t.co/YDaxtE7spF pic.twitter.com/fdQvojpgyh
An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale https://t.co/r5a0RuWyZE v cool. Further steps towards deprecating ConvNets with Transformers. Loving the increasing convergence of Vision/NLP and the much more efficient/flexible class of architectures. pic.twitter.com/muj3cR6uGA
— Andrej Karpathy (@karpathy) October 3, 2020
SCOUTER: An explainable image classifier using a modified version of Slot Attention
— Thomas Kipf (@thomaskipf) September 30, 2020
by Liangzhi Li et al. (Osaka University)
SCOUTER: https://t.co/qcRK1wk6GB
Slot Attention: https://t.co/xfpjQwMuLP pic.twitter.com/u6MfKTwoMj
Want to show off your skills with TensorFlow and deep learning using TPUs? We'd love to see what you can build in response to this task on the Chinese MNIST dataset: https://t.co/Fp66iBWt5h
— Kaggle (@kaggle) September 24, 2020
finetuning data efficient gans 100-shot-obama to cartoonset
— AK (@ak92501) September 23, 2020
github: https://t.co/CZt3YeJ5Gd
dataset: https://t.co/IzSvkrsLyk pic.twitter.com/4vfzvmYpjd
