Have you wondered why object detection, unlike classification, has so many sophisticated algorithms?
— Ting Chen (@tingchenai) September 23, 2021
With Pix2Seq (https://t.co/ygsG3aAIbG), we simply cast object detection as a language modeling task conditioned on pixels!
(with @srbhsxn, Lala Li, @fleet_dj, @geoffreyhinton) pic.twitter.com/aTYZ5IvJc9
Wish your neural networks faster and more accurate?
— Mingxing Tan (@tanmingxing) September 16, 2021
Check out our recent EfficientNetV2 and CoAtNet, which significantly speed up the training and inference, while achieving state-of-the-art 90.88% top-1 accuracy on ImageNet. https://t.co/9buCSZmYby
For downloading large image datasets (1M+), I highly recommend https://t.co/U27VlPBfUK from @rom1504
— Boris Dayma 🥑 (@borisdayma) September 15, 2021
You can even monitor performance and download errors with @weights_biases pic.twitter.com/ZvrHh6B8O0
LAION-400M: open-source dataset of 400 million image-text pairs
— AK (@ak92501) September 12, 2021
project page: https://t.co/IA8aNpXZ6a pic.twitter.com/f5IoLESnRx
ConvMLP: Hierarchical Convolutional MLPs for Vision
— AK (@ak92501) September 10, 2021
pdf: https://t.co/f6c1XmyLSX
abs: https://t.co/vkgXvlCmcD
github: https://t.co/FyjNR8W3Oq pic.twitter.com/RXXJgzoula
Scaled ReLU Matters for Training Vision Transformers
— AK (@ak92501) September 9, 2021
pdf: https://t.co/OcaIFc7Vfl
abs: https://t.co/1k2vrXXsoT pic.twitter.com/glmnhkahWj
We're slowly learning more about Google's not-exactly-public efforts in the huge LM space. The highlight here for me was the subfigure on the right: More evidence that we can see discontinuous, qualitatively-important improvements in behavior as we scale.https://t.co/Q68HaF2Vag pic.twitter.com/yGHmwCLvPt
— Prof. Sam Bowman (@sleepinyourhat) September 7, 2021
Eyes Tell All: Irregular Pupil Shapes Reveal GAN-generated Faces
— AK (@ak92501) September 2, 2021
pdf: https://t.co/lgcfsZO7dp
abs: https://t.co/ZV5TJyVAp4 pic.twitter.com/9BYyrVpxAC
Article in @petapixel about @GoogleAI's SR3 Image Super-resolution method.
— hardmaru (@hardmaru) September 1, 2021
Neural network-based photo upscaling will likely be commonplace in most smartphones in the near future.https://t.co/7TKE3jeTv2
How Can Increased Randomness in Stochastic Gradient Descent Improve Generalization?
— AK (@ak92501) August 24, 2021
pdf: https://t.co/Jsj1hpi3vB
abs: https://t.co/nEGOGZ2Z8v pic.twitter.com/weTbqMbQbF
Do Vision Transformers See Like Convolutional Neural
— AK (@ak92501) August 20, 2021
Networks?
pdf: https://t.co/5Yz5F2PZwO
abs: https://t.co/bpHO2rOYDv
find striking differences between the two architectures, such as ViT having more uniform representations across all layers pic.twitter.com/0KT0KE16f9
SOTR: Segmenting Objects with Transformers
— AK (@ak92501) August 17, 2021
pdf: https://t.co/eplIKD4mgZ
abs: https://t.co/ARAaQ7VJAe
github: https://t.co/XlVZrJh25P
performs well on the MS COCO dataset and surpasses sota instance segmentation approaches pic.twitter.com/06tH3XPtKQ
