dripta_rayc's profile picture. Applied Scientist @ AWS AI

Dripta Raychaudhuri

@dripta_rayc

Applied Scientist @ AWS AI

Dripta Raychaudhuri 已转帖

🛑New Paper Alert!🛑 Introducing POISE for human silhouette extraction! 🤖✨ Our latest research tackles the tricky problem of occlusions with a novel self-supervised approach. (1/5)

take2rohit's tweet image. 🛑New Paper Alert!🛑 
Introducing POISE for human silhouette extraction! 🤖✨ Our latest research tackles the tricky problem of occlusions with a novel self-supervised approach. (1/5)

Come check out our work on Controllable Dynamic Multi-task Architectures at #CVPR2022 oral session 3.1.2 (8.30-10.30am) and poster session 3.1 (10.00-12.30pm) tomorrow June 23! Project page: nec-labs.com/~mas/DYMU/

dripta_rayc's tweet image. Come check out our work on Controllable Dynamic Multi-task Architectures at #CVPR2022 oral session 3.1.2 (8.30-10.30am) and poster session 3.1 (10.00-12.30pm) tomorrow June 23! 

Project page: nec-labs.com/~mas/DYMU/

Dripta Raychaudhuri 已转帖

I get a lot of reviews that say my work is not novel and I bet I'm not alone. It's always frustrating because I see novelty where the reviewer doesn't. Rather than rebut every critique, I've written a blog post to help reviewers think about novelty. perceiving-systems.blog/en/news/novelt…


Dripta Raychaudhuri 已转帖

Errr ok wow, I am shook by the new ConvMixer architecture openreview.net/forum?id=TVHS5… "the first model that achieves the elusive dual goals of 80%+ ImageNet top-1 accuracy while also fitting into a tweet" 😐

karpathy's tweet image. Errr ok wow, I am shook by the new ConvMixer architecture
openreview.net/forum?id=TVHS5… "the first model that achieves the elusive dual goals of 80%+ ImageNet top-1 accuracy while also fitting into a tweet" 😐

Loading...

Something went wrong.


Something went wrong.