Loss Functions

Gradient Harmonizing Mechanism C

Introduced by Li et al. in Gradient Harmonized Single-stage Detector

GHM-C is a loss function designed to balance the gradient flow for anchor classification. The GHM first performs statistics on the number of examples with similar attributes w.r.t their gradient density and then attaches a harmonizing parameter to the gradient of each example according to the density. The modification of gradient can be equivalently implemented by reformulating the loss function. Embedding the GHM into the classification loss is denoted as GHM-C loss. Since the gradient density is a statistical variable depending on the examples distribution in a mini-batch, GHM-C is a dynamic loss that can adapt to the change of data distribution in each batch as well as to the updating of the model.

Source: Gradient Harmonized Single-stage Detector


Paper Code Results Date Stars


Task Papers Share
General Classification 1 33.33%
Object Detection 1 33.33%
Philosophy 1 33.33%


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