Hyper-Convolutions via Implicit Kernels for Medical Imaging — mentioned by neodypsis

Sun, 21 May 2023 22:19:48 GMT

> We propose the nested network architecture since it shares the parameters via repetitions of sub-network activation functions. In other words, a NestNet can provide a special parameter-sharing scheme. This is the key reason why the NestNet has much better approximation power than the standard network. 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.…

Paper and discussion history. A mention is not an endorsement.

Hyper-Convolutions via Implicit Kernels for Medical Imaging · HackerPapers discussions

Hyper-Convolutions via Implicit Kernels for Medical Imaging — mentioned by neodypsis