Here's a link to the paper: https://t.co/MqnfIqmUHC
— Jeremy Howard (@jeremyphoward) February 21, 2019
Here's a link to the paper: https://t.co/MqnfIqmUHC
— Jeremy Howard (@jeremyphoward) February 21, 2019
*Adaptive Cross-Modal Few-Shot Learning* is on arXiv now.
— Negar Rostamzadeh (@negar_rz) February 20, 2019
Chen Xing, me, Boris Oreshkin and Pedro Pinheirohttps://t.co/JsCqMZRYZh pic.twitter.com/wFP7W2uNiW
Grrr... I forgot the link! Here it is: https://t.co/PbReNdsbZs https://t.co/dbOSL97jkc
— Jeremy Howard (@jeremyphoward) February 11, 2019
The DL CV community is having a "oh wait, bags of local features are a really strong baseline for classification" moment with the BagNet paper.
— Alec Radford (@AlecRad) February 11, 2019
This has always been clear for text classification due to n-gram baselines. It took an embarrassingly long time for nets to beat them.
PyTorch implementation of "Super-Realtime Facial Landmark Detection and Shape Fitting by Deep Regression of Shape Model Parameters" https://t.co/kAFzsIElJx #deeplearning #machinelearning #ml #ai #neuralnetworks #datascience #pytorch
— PyTorch Best Practices (@PyTorchPractice) February 10, 2019
Why don't modern architectures use the Inception stem? Did people try it and find it doesn't help over 3 3x3 convs? Or has it been forgotten?
— Jeremy Howard (@jeremyphoward) February 10, 2019
It seems like a smart design to me, but I haven't done experiments...
FAIR has released code for the robust ImageNet model by Cihang Xie et al: https://t.co/yB53YRJIUP
— Ian Goodfellow (@goodfellow_ian) February 8, 2019
NVIDIA's StyleGAN implementation just open-sourced. Very cool stuff, please use responsibly! https://t.co/9P83Ohzf1d
— Eric Jang (@ericjang11) February 6, 2019
One of those papers where the #nlproc person in me asks, “wait a sec, why wasn’t this a baseline in that community until now?” https://t.co/FlzAZrtyhU
— Delip Rao (@deliprao) February 2, 2019
New @MIT study shows gender and racial bias in @amazon Rekognition AI product -100% accuracy on pale males vs 69% accuracy on women of colorhttps://t.co/lkWce4hR5a - Study link https://t.co/3aU83ETcRG @ACLU @Data4BlackLives @black_in_ai @medialab @AIESConf @AINowInstitute @AOC pic.twitter.com/YsloeUE2yz
— Joy Buolamwini (@jovialjoy) January 25, 2019
Yes very much so. Well spotted. There are "Group Equivariant Convolutional Networks" and other related papers in this area, although there's still much work to be done. https://t.co/aTQkwZzD4m https://t.co/ZmXDFjMU3Z
— Jeremy Howard (@jeremyphoward) January 24, 2019
"How to visualize convolutional features in 40 lines of code" by Fabio M. Graetz
— Jeremy Howard (@jeremyphoward) January 24, 2019
Amazingly cool (and simple!) approach to visualizing convolutional features using fastai and @PyTorch (it uses the older fastai 0.7 and pytorch 0.4).https://t.co/QfAtBtzuIP pic.twitter.com/AeGge1AUkj