Reputation: 645
What is the general logic behind choosing the weight for calculating weighted sigmoid cross-entropy loss, or for any weighted loss in case of an imbalanced dataset? The problem domain is based on vision/image classification.
Upvotes: 2
Views: 2848
Reputation: 1427
A good reference would be this CVPR '19 paper: "Class-Balanced Loss Based on Effective Number of Samples". In the paper, they've used an re-weighting scheme that uses the effective number of samples for each-class to re-balance the loss for handling inter-class imbalance issues. You could also refer a Medium article explaining the same research work.
Upvotes: 2