# Multi-Loss Weighting with Coefficient of Variations

arXiv: https://arxiv.org/abs/2009.01717 · HTML: https://mlsanity.com/paper/2009.01717/

## Key facts

- Cited by 36 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Sep 2020.

## Built on by (most cited first, 30 of 36)

- [Using Sequences of Life-events to Predict Human Lives](https://mlsanity.com/paper/2306.03009/) (2023)
- [Real-time Neural Network Inference on Extremely Weak Devices: Agile Offloading with Explainable AI](https://mlsanity.com/paper/2312.14229/) (2023)
- [Exploiting Unlabelled Photos for Stronger Fine-Grained SBIR](https://mlsanity.com/paper/2303.13779/) (2023)
- [Bayesian Learning-driven Prototypical Contrastive Loss for Class-Incremental Learning](https://mlsanity.com/paper/2405.11067/) (2024)
- [Learning Temporally-Consistent Representations for Data-Efficient Reinforcement Learning](https://mlsanity.com/paper/2110.04935/) (2021)
- [Gradient Remedy for Multi-Task Learning in End-to-End Noise-Robust Speech Recognition](https://mlsanity.com/paper/2302.11362/) (2023)
- [Training multi-objective/multi-task collocation physics-informed neural network with student/teachers transfer learnings](https://mlsanity.com/paper/2107.11496/) (2021)
- [SEER: Self-Aligned Evidence Extraction for Retrieval-Augmented Generation](https://mlsanity.com/paper/2410.11315/) (2024)
- [CrossAligner & Co: Zero-Shot Transfer Methods for Task-Oriented Cross-lingual Natural Language Understanding](https://mlsanity.com/paper/2203.09982/) (2022)
- [Personalized Predictions of Glioblastoma Infiltration: Mathematical Models, Physics-Informed Neural Networks and Multimodal Scans](https://mlsanity.com/paper/2311.16536/) (2023)
- [Rethinking Generic Camera Models for Deep Single Image Camera Calibration to Recover Rotation and Fisheye Distortion](https://mlsanity.com/paper/2111.12927/) (2021)
- [A Clustering-guided Contrastive Fusion for Multi-view Representation Learning](https://mlsanity.com/paper/2212.13726/) (2022)
- [MergeNet: Knowledge Migration across Heterogeneous Models, Tasks, and Modalities](https://mlsanity.com/paper/2404.13322/) (2024)
- [HaloAE: An HaloNet based Local Transformer Auto-Encoder for Anomaly Detection and Localization](https://mlsanity.com/paper/2208.03486/) (2022)
- [A Solver-Free Framework for Scalable Learning in Neural ILP Architectures](https://mlsanity.com/paper/2210.09082/) (2022)
- [Hallucination Diversity-Aware Active Learning for Text Summarization](https://mlsanity.com/paper/2404.01588/) (2024)
- [Dual-Balancing for Physics-Informed Neural Networks](https://mlsanity.com/paper/2505.11117/) (2025)
- [Disentangling Transfer and Interference in Multi-Domain Learning](https://mlsanity.com/paper/2107.05445/) (2021)
- [PriMask: Cascadable and Collusion-Resilient Data Masking for Mobile Cloud Inference](https://mlsanity.com/paper/2211.06716/) (2022)
- [B-BACN: Bayesian Boundary-Aware Convolutional Network for Crack Characterization](https://mlsanity.com/paper/2302.06827/) (2023)
- [gcDLSeg: Integrating Graph-cut into Deep Learning for Binary Semantic Segmentation](https://mlsanity.com/paper/2312.04713/) (2023)
- [A Multi-Task Learning Approach to Linear Multivariate Forecasting](https://mlsanity.com/paper/2502.03571/) (2025)
- [Learning from Physical Human Feedback: An Object-Centric One-Shot Adaptation Method](https://mlsanity.com/paper/2203.04951/) (2022)
- [Elastic Multi-Gradient Descent for Parallel Continual Learning](https://mlsanity.com/paper/2401.01054/) (2024)
- [Adaptive Real-Time Multi-Loss Function Optimization Using Dynamic Memory Fusion Framework: A Case Study on Breast Cancer Segmentation](https://mlsanity.com/paper/2410.19745/) (2024)
- [GENRE-CMR: Generalizable Deep Learning for Diverse Multi-Domain Cardiac MRI Reconstruction](https://mlsanity.com/paper/2508.20600/) (2025)
- [MetaPerch: Learning from metadata for bioacoustics foundation models](https://mlsanity.com/paper/2607.14072/) (2026)
- [NeurIT: Pushing the Limit of Neural Inertial Tracking for Indoor Robotic IoT](https://mlsanity.com/paper/2404.08939/) (2024)
- [Variational Model Merging for Pareto Front Estimation in Multitask Finetuning](https://mlsanity.com/paper/2412.08147/) (2024)
- [Consistent multi-animal pose estimation in cattle using dynamic Kalman filter based tracking](https://mlsanity.com/paper/2503.10450/) (2025)

## Abstract (arXiv)

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.