search

yaoyao-liu / class-incremental-learning

PyTorch implementation of AANets (CVPR 2021) and Mnemonics Training (CVPR 2020 Oral)
https://class-il.mpi-inf.mpg.de
MIT License
459 stars 71 forks source link

What does the flag `--fusion_mode` represent? #7

Closed Michaelyq closed 4 years ago

Michaelyq commented 4 years ago

Hi, I notice that the target model in the squential class-incremental training is set to network_mtl. Regarding your implementation for constructing an "mtl" network, it seems every weight of convolution kernels is freezed and multiplied by a learnable mask (initialized as 1). My question is why the network architecture is implemented in this way?

Thanks in adavance! Michael

yaoyao-liu commented 4 years ago

Thanks for your interest in our work.

We deploy weight transfer operations to train the weight scaling and shifting parameters. The aim is to preserve the structural knowledge of the previous model. Please kindly refer to the Supplementary materials, Section B for details: arXiv link.