# Steerable Pyramid Weighted Loss: Multi-Scale Adaptive Weighting for Semantic Segmentation

arXiv: https://arxiv.org/abs/2503.06604 · HTML: https://mlsanity.com/paper/2503.06604/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 29 references that are in the map.
- First posted on arXiv 9 Mar 2025.

## Builds on (most cited first, 14 of 14)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation](https://mlsanity.com/paper/1606.04797/) (2016)
- [clDice -- A Novel Topology-Preserving Loss Function for Tubular Structure Segmentation](https://mlsanity.com/paper/2003.07311/) (2020)
- [Tversky loss function for image segmentation using 3D fully convolutional deep networks](https://mlsanity.com/paper/1706.05721/) (2017)
- [Gland Segmentation in Colon Histology Images: The GlaS Challenge Contest](https://mlsanity.com/paper/1603.00275/) (2016)
- [InverseForm: A Loss Function for Structured Boundary-Aware Segmentation](https://mlsanity.com/paper/2104.02745/) (2021)
- [Region Mutual Information Loss for Semantic Segmentation](https://mlsanity.com/paper/1910.12037/) (2019)
- [Loss Functions in the Era of Semantic Segmentation: A Survey and Outlook](https://mlsanity.com/paper/2312.05391/) (2023)
- [Boundary Loss for Remote Sensing Imagery Semantic Segmentation](https://mlsanity.com/paper/1905.07852/) (2019)
- [Machine learning of hierarchical clustering to segment 2D and 3D images](https://mlsanity.com/paper/1303.6163/) (2013)
- [Multiclass Weighted Loss for Instance Segmentation of Cluttered Cells](https://mlsanity.com/paper/1802.07465/) (2018)
- [Enhancing Boundary Segmentation for Topological Accuracy with Skeleton-based Methods](https://mlsanity.com/paper/2404.18539/) (2024)
- [Complex Wavelet Mutual Information Loss: A Multi-Scale Loss Function for Semantic Segmentation](https://mlsanity.com/paper/2502.00563/) (2025)

## Built on by (most cited first, 1 of 1)

- [IMSAHLO: Integrating Multi-Scale Attention and Hybrid Loss Optimization Framework for Robust Neuronal Brain Cell Segmentation](https://mlsanity.com/paper/2601.11645/) (2026)

## Abstract (arXiv)

Semantic segmentation is a core task in computer vision with applications in biomedical imaging, remote sensing, and autonomous driving. While standard loss functions such as cross-entropy and Dice loss perform well in general cases, they often struggle with fine structures, particularly in tasks involving thin structures or closely packed objects. Various weight map-based loss functions have been proposed to address this issue by assigning higher loss weights to pixels prone to misclassification. However, these methods typically rely on precomputed or runtime-generated weight maps based on distance transforms, which impose significant computational costs and fail to adapt to evolving network predictions. In this paper, we propose a novel steerable pyramid-based weighted (SPW) loss function that efficiently generates adaptive weight maps. Unlike traditional boundary-aware losses that depend on static or iteratively updated distance maps, our method leverages steerable pyramids to dynamically emphasize regions across multiple frequency bands (capturing features at different scales) while maintaining computational efficiency. Additionally, by incorporating network predictions into the weight computation, our approach enables adaptive refinement during training. We evaluate our method on the SNEMI3D, GlaS, and DRIVE datasets, benchmarking it against 11 state-of-the-art loss functions. Our results demonstrate that the proposed SPW loss function achieves superior pixel precision and segmentation accuracy with minimal computational overhead. This work provides an effective and efficient solution for improving semantic segmentation, particularly for applications requiring multiscale feature representation. The code is avaiable at https://anonymous.4open.science/r/SPW-0884