798 karma · joined May 26, 2015
It would be interesting to see an experiment that compares their CNN2 model with other parameter-sharing schemes such as networks using hyper-convolutions [0][1][2].
[0] Ma, T., Wang, A. Q., Dalca, A. V., & Sabuncu, M. R. (2022). Hyper-Convolutions via Implicit Kernels for Medical Imaging. arXiv preprint arXiv:2202.02701.
[1] Chang, O., Flokas, L., & Lipson, H. (2019, September). Principled weight initialization for hypernetworks. In International Conference on Learning Representations.
[2] Ukai, K., Matsubara, T., & Uehara, K. (2018, November). Hypernetwork-based implicit posterior estimation and model averaging of cnn. In Asian Conference on Machine Learning (pp. 176-191). PMLR.
Their website: https://rescript-lang.org/
[0] https://www.edx.org/xseries/mitx-circuits-and-electronics
You mean like in an U-Net architecture?
> What I’m saying is that washing clothes doesn’t seem to benefit from any QR codes. And the cooking example is even more confusing because presumably you’d have one for the recipe, not per ingredient
Well, we are in the age of IoT. Every appliance now wants to be connected to the Internet.
Presumably they are using object detection to recognize where the QR codes are located in the image? Which they then feed to the standard QR decoding algorithms.
I fail to see how my comment could be interpreted as a commercial for Lockdown Mode. Unfortunately, we are living at times where everyone now carries a device in their pocket with a reliable Internet connection, a microphone and a camera; and such devices have demonstrated consistently to be vulnerable to nefarious actors.
Cool. That's good to hear, thanks for sharing your experience!