# Adaptive Real-Time Multi-Loss Function Optimization Using Dynamic Memory Fusion Framework: A Case Study on Breast Cancer Segmentation

arXiv: https://arxiv.org/abs/2410.19745 · HTML: https://mlsanity.com/paper/2410.19745/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 39 references that are in the map.
- First posted on arXiv 10 Oct 2024.

## Builds on (most cited first, 8 of 8)

- [A General and Adaptive Robust Loss Function](https://mlsanity.com/paper/1701.03077/) (2017)
- [SoftAdapt: Techniques for Adaptive Loss Weighting of Neural Networks with Multi-Part Loss Functions](https://mlsanity.com/paper/1912.12355/) (2019)
- [Multi-Loss Weighting with Coefficient of Variations](https://mlsanity.com/paper/2009.01717/) (2020)
- [Dynamic Loss For Robust Learning](https://mlsanity.com/paper/2211.12506/) (2022)
- [OWAdapt: An adaptive loss function for deep learning using OWA operators](https://mlsanity.com/paper/2305.19443/) (2023)
- [FuseFormer: A Transformer for Visual and Thermal Image Fusion](https://mlsanity.com/paper/2402.00971/) (2024)
- [A Dynamically Weighted Loss Function for Unsupervised Image Segmentation](https://mlsanity.com/paper/2403.11266/) (2024)
- [Phase Aberration Correction without Reference Data: An Adaptive Mixed Loss Deep Learning Approach](https://mlsanity.com/paper/2303.05747/) (2023)

## Built on by (most cited first, 2 of 2)

- [GCond: Gradient Conflict Resolution via Accumulation-based Stabilization for Large-Scale Multi-Task Learning](https://mlsanity.com/paper/2509.07252/) (2025)
- [QiVC-Net: Quantum-Inspired Variational Convolutional Network, with Application to Biosignal Classification](https://mlsanity.com/paper/2511.05730/) (2025)

## Abstract (arXiv)

Deep learning has proven to be a highly effective tool for a wide range of applications, significantly when leveraging the power of multi-loss functions to optimize performance on multiple criteria simultaneously. However, optimal selection and weighting loss functions in deep learning tasks can significantly influence model performance, yet manual tuning of these functions is often inefficient and inflexible. We propose a novel framework called dynamic memory fusion for adaptive multi-loss function penalizing in real-time to address this. This framework leverages historical loss values data to dynamically adjust the weighting of multiple loss functions throughout the training process. Additionally, this framework integrates an auxiliary loss function to enhance model performance in the early stages. To further research horizons, we introduce the class-balanced dice loss function, designed to address class imbalance by prioritizing underrepresented classes. Experiments on breast ultrasound datasets demonstrate that the framework improves segmentation performance across various metrics. These results demonstrate the effectiveness of our proposed framework in ensuring that the model dynamically adjusts its focus to prioritize the most relevant criteria, leading to improved performance in evolving environments. The source code for our proposed methodology is publicly available on GitHub.