#ImageNet

Does higher performance on ImageNet translate to higher performance on medical imaging tasks?Surprisingly, the answer is no!We investigate their relationship.Paper: https://arxiv.org/abs/2101.06871 @_alexke, William Ellsworth, Oishi Ba
Read more
Seems there is a lot of harping on the details of the @DeepMind protein folding solution. Some of the concerns are legitimate, but in my mind even those are overblown.
Read more
1/5 In July 2016, Jitendra Malik gave an inspiring talk at Google, with a slide showing a block diagram of visual pathway in a primate. He said "there are a
Read more
Really impressed with CLIP, @OpenAI's recent model for image classification. I think it could change a LOT about how we train models.Little summary CLIP is a new* image model
Read more
Researchers make terrible futurists. Really. Why? Several reasons:(1) Because they spend their days trying to solve really hard problems. They experience 99.9% "hard" and "it doesn't work yet". This induces
Read more
NEW from a big collaboration at Google: Underspecification Presents Challenges for Credibility in Modern Machine LearningExplores a common failure mode when applying ML to real-world problems. 1/14https://arxiv.org/abs/2011.03395  We
Read more
Artificial Intelligence and Machine Learning trends in 2020 Short overview of the fields where AI and ML is growing fast. Thread Robotics Traditional robotics algorithms like localization, mapping, path
Read more
If I were starting grad school now I would not do a PhD in ML. It's not the competition that would steer me away though, I think it's a bad
Read more
Yann, I know you mean well. I saw many people act like you just did in good faith, and get defensive when people pointed that this was not the proper
Read more
Why does @OpenAI's CLIP model matter?https://openai.com/blog/clip/  Traditionally, training a classification model (a "thing labeler") relies on collecting a lot of images of your specific thing. This is effective, but br
Read more
This is the first thing I also thought of after seeing this thread! If you're interested in computer vision x fairness, here are some good introductory papers I like:https://twitter.com/rahulkrdass/status/1275297369920331776 Some
Read more
What are Convolutional Neural Networks? CNNs are an important class of deep artificial neural networks that are particularly well suited for images.If you want to learn the important
Read more
By continuing to use the site, you are consenting to the use of cookies as explained in our Cookie Policy to improve your experience.