Discover and read the best of Twitter Threads about #ContinuousTimeMethods
Most recents (1)
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?π€Yes! Meet the ππππ, a single CNN that achieves SOTA on several datasets, e.g., LRA!π₯
Can we design a single CNN that works well on all these settings?π€Yes! Meet the ππππ, a single CNN that achieves SOTA on several datasets, e.g., LRA!π₯
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/cβ¦
Slides: app.slidebean.com/p/gk5j826nq7/Cβ¦
Joint work with @davidknigge, @_albertgu, @erikjbekkers, @egavves, @jmtomczak & Mark Hoogendoorn.
Paper: arxiv.org/abs/2206.03398
Code: github.com/david-knigge/cβ¦
Slides: app.slidebean.com/p/gk5j826nq7/Cβ¦
πππ’π§ ππππ: Architecture changes are needed to model long range dependencies for signals of different length, res & dims, e.g., pooling, depth, kernel sizes.
To solve all tasks with a single CNN, it must model long range deps. at every layer: use Continuous Conv Kernels!
To solve all tasks with a single CNN, it must model long range deps. at every layer: use Continuous Conv Kernels!
