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"
Python
Issues
- 3
I've observed a difference in my results. Could you please help me understand the reason behind this discrepancy
#7 opened by WangYJ-WYJ - 1
I cannot reproduce the training results on the CIFAR100 dataset, especially in the last few incremental sessions.
#8 opened by lzwqjh - 2
produce training rect
#6 opened by gulzainali98 - 2
Maybe some bugs for CIFAR100
#5 opened by jinly0513 - 9
Low accuracy for session bigger than 1
#4 opened by fransiskusyoga - 3
cannot reproduce the results on CIFAR100
#3 opened by JungHunOh