NeuralCollapseApplications / FSCIL

[ICLR 2023] The official code for our ICLR 2023 (top25%) paper: "Neural Collapse Inspired Feature-Classifier Alignment for Few-Shot Class-Incremental Learning"

NeuralCollapseApplications/FSCIL Issues

I've observed a difference in my results. Could you please help me understand the reason behind this discrepancy
Closed 6 months ago3
I cannot reproduce the training results on the CIFAR100 dataset, especially in the last few incremental sessions.
Closed 6 months ago1
produce training rect
Closed a year ago2
Maybe some bugs for CIFAR100
Closed a year ago2
Low accuracy for session bigger than 1
Closed a year ago9
cannot reproduce the results on CIFAR100
Closed a year ago3