Methods › General › Loss Functions › Self-Adjusting Smooth L1 Loss

Self-Adjusting Smooth L1 Loss

1 paper tagged archive 2025-07-28

Introduced by Cheng-Yang Fu et al. in RetinaMask: Learning to predict masks improves state-of-the-art single-shot detection for free

archive 2025-07-28 Description, source and code snippet are the archive's method entry.

Self-Adjusting Smooth L1 Loss is a loss function used in object detection that was introduced with RetinaMask. This is an improved version of Smooth L1. For Smooth L1 loss we have:

f(x) = 0.5 x²/β if |x| < β f(x) = |x| -0.5β otherwise

Here a point β splits the positive axis range into two parts: L2 loss is used for targets in range [0, β], and L1 loss is used beyond β to avoid over-penalizing utliers. The overall function is smooth (continuous, together with its derivative). However, the choice of control point (β) is heuristic and is usually done by hyper parameter search.

Instead, with self-adjusting smooth L1 loss, inside the loss function the running mean and variance of the absolute loss are recorded. We use the running minibatch mean and variance with a momentum of $0.9$ to update these two parameters.

PaperSourceSee Code · chengyangfu/retinamask

Papers archive 2025-07-28

1 shown of 1, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.

Tasks archive 2025-07-28

1 task the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.

TaskPapers
Object Detection1

Usage over time archive 2025-07-28

Papers per year tagged with Self-Adjusting Smooth L1 Loss: 2019 to 2019, peak 1 1 0 2019: 1 paper 2019
Papers per year the archive tags with this method, by the paper's archive date (1 dated). Bars are counts, not a trend claim.

Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).

Categories archive 2025-07-28

Loss Functions

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections