Loss Functions

Varifocal Loss

Introduced by Zhang et al. in VarifocalNet: An IoU-aware Dense Object Detector

Varifocal Loss is a loss function for training a dense object detector to predict the IACS, inspired by focal loss. Unlike the focal loss that deals with positives and negatives equally, Varifocal Loss treats them asymmetrically.

$$ VFL\left(p, q\right) = −q\left(q\log\left(p\right) + \left(1 − q\right)\log\left(1 − p\right)\right) \text{ if } q > 0 $$

$$ VFL\left(p, q\right) = −\alpha{p^{\gamma}}\log\left(1-p\right) $$

where $p$ is the predicted IACS and $q$ is the target IoU score.

For a positive training example, $q$ is set as the IoU between the generated bounding box and the ground-truth one (gt IoU), whereas for a negative training example, the training target $q$ for all classes is $0$.

Source: VarifocalNet: An IoU-aware Dense Object Detector


Paper Code Results Date Stars


Task Papers Share
Object Detection 3 42.86%
Small Object Detection 1 14.29%
Instance Segmentation 1 14.29%
Semantic Segmentation 1 14.29%
General Classification 1 14.29%


Component Type
🤖 No Components Found You can add them if they exist; e.g. Mask R-CNN uses RoIAlign