Combo Loss

https://arxiv.org/abs/1805.02798

Combo Loss: Handling Input and Output Imbalance in Multi-Organ Segmentation

 

Combo Loss는  거짓 긍정 또는 거짓 부정에 각각 페널티를 주는 추가 상수가 있는 CELoss와 Dice Loss의 조합입니다.

 

#PyTorch
ALPHA = 0.5 # < 0.5 penalises FP more, > 0.5 penalises FN more
CE_RATIO = 0.5 #weighted contribution of modified CE loss compared to Dice loss

class ComboLoss(nn.Module):
    def __init__(self, weight=None, size_average=True):
        super(ComboLoss, self).__init__()

    def forward(self, inputs, targets, smooth=1, alpha=ALPHA, beta=BETA, eps=1e-9):
        
        #flatten label and prediction tensors
        inputs = inputs.view(-1)
        targets = targets.view(-1)
        
        #True Positives, False Positives & False Negatives
        intersection = (inputs * targets).sum()    
        dice = (2. * intersection + smooth) / (inputs.sum() + targets.sum() + smooth)
        
        inputs = torch.clamp(inputs, eps, 1.0 - eps)       
        out = - (ALPHA * ((targets * torch.log(inputs)) + ((1 - ALPHA) * (1.0 - targets) * torch.log(1.0 - inputs))))
        weighted_ce = out.mean(-1)
        combo = (CE_RATIO * weighted_ce) - ((1 - CE_RATIO) * dice)
        
        return combo

출처 : https://www.kaggle.com/code/sungjunghwan/loss-function-of-image-segmentation