Striking the Right Balance: Recall Loss for Semantic Segmentation
Junjiao Tian,Niluthpol Chowdhury Mithun,Zachary Seymour,Han-Pang Chiu,Zsolt Kira,Junjiao Tian,Niluthpol Chowdhury Mithun,Zachary Seymour,Han-Pang Chiu,Zsolt Kira
Class imbalance is a fundamental problem in computer vision applications such as semantic segmentation. Specifically, uneven class distributions in a training dataset often result in unsatisfactory performance on under-represented classes. Many works have proposed to weight the standard cross entropy loss function with pre-computed weights based on class statistics, such as the number of samples a...
