Closed shivashankarrs closed 3 years ago
LDAM-DRW and Focal Loss https://github.com/kaidic/LDAM-DRW/blob/master/losses.py
Self-adjusted Dice Loss https://github.com/fursovia/self-adj-dice/blob/master/sadice/loss.py
Class-balanced loss based on effective number of samples (uses focal) https://github.com/vandit15/Class-balanced-loss-pytorch/blob/master/class_balanced_loss.py
List of many losses: https://github.com/JunMa11/SegLoss
There are two main approaches: (1) resampling and (2) reweighting/loss.
The resampling and reweighting approaches can be combined (as in ldam-drw).
Yeah right, we will require some implementations for resampling as well. Resampling with some dropouts is a reasonable way I think, has anyone done it?, or they just duplicate?
balanced sampling of imbalanced datasets easy to use library (will equate oversampling) https://github.com/ufoym/imbalanced-dataset-sampler
We have all objective based losses.
Implement/refactor class imbalance approaches, with easy to use api calls.