Multi-Loss Weighting with Coefficient of Variations

TL;DR

This paper introduces a novel loss weighting scheme based on the coefficient of variations that dynamically balances multiple losses during training without additional hyperparameter tuning, improving single-task learning.

Contribution

The paper proposes a coefficient of variation-based loss weighting method that adapts during training for single-task multi-loss problems, avoiding extensive hyperparameter search.

Findings

Effective in depth estimation tasks across multiple datasets

Improves semantic segmentation performance

Reduces need for hyperparameter tuning

Abstract

Many interesting tasks in machine learning and computer vision are learned by optimising an objective function defined as a weighted linear combination of multiple losses. The final performance is sensitive to choosing the correct (relative) weights for these losses. Finding a good set of weights is often done by adopting them into the set of hyper-parameters, which are set using an extensive grid search. This is computationally expensive. In this paper, we propose a weighting scheme based on the coefficient of variations and set the weights based on properties observed while training the model. The proposed method incorporates a measure of uncertainty to balance the losses, and as a result the loss weights evolve during training without requiring another (learning based) optimisation. In contrast to many loss weighting methods in literature, we focus on single-task multi-loss problems, such as monocular depth estimation and semantic segmentation, and show that multi-task approaches for loss weighting do not work on those single-tasks. The validity of the approach is shown empirically for depth estimation and semantic segmentation on multiple datasets.