Newbeeer / L_DMI

Code for NeurIPS 2019 Paper, "L_DMI: An Information-theoretic Noise-robust Loss Function"

Newbeeer/L_DMI Issues

您好，如何才能具有访问链接的权限？
Closed a year ago5
new datasets/ noisy instances
Updated a year ago1
Error in fashion.py
Updated 2 years ago
DMI_loss
Closed 2 years ago2
It seems that this new loss can also be used for clean data?
Closed 3 years ago1
Confusion Matrix
Closed 3 years ago1
Negative Loss Values and a Strange Issue
Closed 3 years ago1
Negative loss values
Closed 4 years ago3
Can this loss can be use for multi label classification?
Updated 4 years ago
Why bad performance without model pre-training?
Closed 4 years ago1
det() always equals 0 when the number of categories is much larger than batch size, e.g., 700 classes v.s. 64 batch.
Closed 4 years ago1
why dmi loss need to add '0.001' to det(mat)+0.001
Closed 4 years ago2
Clothing1M数据集下载
Closed 5 years ago3
clothing1M
Closed 5 years ago4
For Clothing1M dataset, how many GPU memory are needed?
Closed 5 years ago2
Help on running L_DMI
Closed 5 years ago3