Equalization Loss

📅 2022/5/17 · ☕ 1 min read

headはlossを小さく, tailはlossを大きくしたい
重み $w_{i}$ を使ってlossを設計する (二値の場合)
$L_{E Q L} = - \sum_{j = 1}^{C} w_{j} l o g (\hat{p_{j}}),$ $w_{j} = 1 - E (r) T_{λ} (f_{j}) (1 - y_{j})$

In this equation, E(r) outputs 1 when r is a foreground region proposal and 0 when it belongs to background. And fj is the frequency of category j in the dataset, which is computed by the image number of the class j over the image number of the entire dataset. And Tλ(x) is a threshold function which outputs 1 when x < λ and 0 otherwise. λ is utilized to distinguish tail categories from all other categories and Tail Ratio (T R) is used as the criterion to set the value of it