Share this page!

Enter URL or ID to Unroll

You can paste full URL like: https://x.com/threadreaderapp/status/1644127596119195649
or just the ID like: 1644127596119195649

How to get URL link on X (Twitter) App

  1. On the Twitter thread, click on or icon on the bottom
  2. Click again on or Share Via icon
  3. Click on Copy Link to Tweet
  4. Paste it above and click "Unroll Thread"!
  5. More info at Twitter Help
David W. Romero Profile picture
David W. Romero
@davidwromero
Research Scientist @NVIDIA. PhD Candidate Efficient DL @VUAmsterdam. Prev: @Merl_news, @Qualcomm, @GoogleAI. Opinions my own.
Jul 5, 2022 • 10 tweets • 6 min read
VGG, U-Net, TCN, ... CNNs are powerful but must be tailored to specific problems, data-types, -lenghts & -resolutions.

Can we design a single CNN that works well on all these settings?🤔Yes! Meet the 𝐂𝐂𝐍𝐍, a single CNN that achieves SOTA on several datasets, e.g., LRA!🔥 Accepted at the #ICML2022 #Workshop on #ContinuousTimeMethods.

Joint work with @davidknigge, @_albertgu, @erikjbekkers, @egavves, @jmtomczak & Mark Hoogendoorn.

Paper: arxiv.org/abs/2206.03398
Code: github.com/david-knigge/c…
Slides: app.slidebean.com/p/gk5j826nq7/C…
Oct 19, 2021 • 11 tweets • 6 min read
CNNs ask you to predefine the size of conv. kernels. But, isn't it better to let the network decide?

Our new work w/ @rjbruin let CNNs learn full-res. kernels during training, leading to SOTA on several datasets!😀

Code & slides here!
w/ @jmtomczak @erikjbekkers & @jan_gemert Paper: arxiv.org/abs/2110.08059
Code: github.com/rjbruin/flexco…
Slides: app.slidebean.com/p/ef4087axxj/F…
Poster: github.com/rjbruin/flexco…