Focal Loss: Focus on What’s Hard
A Novel Loss to address Class Imbalance for the Object detection
Published in
6 min readApr 7, 2021
You will learn about Focal loss, how it is used in Object detection to detect hard negative examples, and then implement Focal loss for an imbalanced dataset.
Focal loss is based on the premise where the training focuses on a sparse set of hard examples and prevents the vast…