"Exploring Complementary Strengths of Invariant and Equivariant Representations for Few-Shot Learning" by Mamshad Nayeem Rizve, Salman Khan, Fahad Shahbaz Khan, Mubarak Shah (CVPR 2021)
I've reproduced results for CIFAR-FS and FC100, but I failed when I tried to reproduce the paper accuracies on miniImageNet.
Could you share the pretrained model on miniImageNet and tieredImageNet ? or give some tips?
Thanks
It's a really nice work. While I've reproduced your results for CIFAR-FS and FC100, training miniImageNet and tieredImageNet requires huge memories of GPU and time (it could not fit into 4 x RTX2080Ti). Is that possible you can share pretrained models (both base and distilled) for those two benchmarks in Dropbox or Google Drive? That will be really helpful.