# Automated Focal Loss for Image based Object Detection

## TL;DR

This paper introduces an automated focal loss that adapts during training, reducing hyperparameter tuning and accelerating convergence in object detection tasks, with improved performance in 2D and 3D detection benchmarks.

## Contribution

The paper presents an automated focal loss that replaces manual hyperparameters with an adaptive parameter, enhancing training efficiency and detection accuracy.

## Key findings

- Up to 30% faster training convergence on COCO
- Outperforms other loss functions in 3D vehicle detection by 1.8 AOS
- Provides a range-independent metric for regression tasks

## Abstract

Current state-of-the-art object detection algorithms still suffer the problem of imbalanced distribution of training data over object classes and background. Recent work introduced a new loss function called focal loss to mitigate this problem, but at the cost of an additional hyperparameter. Manually tuning this hyperparameter for each training task is highly time-consuming. With automated focal loss we introduce a new loss function which substitutes this hyperparameter by a parameter that is automatically adapted during the training progress and controls the amount of focusing on hard training examples. We show on the COCO benchmark that this leads to an up to 30% faster training convergence. We further introduced a focal regression loss which on the more challenging task of 3D vehicle detection outperforms other loss functions by up to 1.8 AOS and can be used as a value range independent metric for regression.