可操纵金字塔加权损失：面向语义分割的多尺度自适应加权
Steerable Pyramid Weighted Loss: Multi-Scale Adaptive Weighting for Semantic Segmentation
AI总结：
本文提出基于可操纵金字塔的SPW损失函数，利用多频带动态生成自适应权重图并结合网络预测进行细化，在三个数据集上以低计算开销超越11种主流损失函数，显著提升精细结构分割精度。
摘要：
语义分割是计算机视觉中的核心任务，广泛应用于生物医学成像、遥感与自动驾驶等领域。虽然交叉熵和Dice损失等标准损失函数在一般场景下表现良好，但在处理精细结构时往往力不从心，尤其是在涉及细薄结构或紧密排列对象的任务中。为此，已有多种基于权重图的损失函数被提出，通过对易误分类像素赋予更高损失权重来缓解该问题。然而，这些方法通常依赖基于距离变换的预计算或运行时生成的权重图，不仅计算开销大，而且难以适应网络预测的动态变化。本文提出一种新颖的基于可操纵金字塔的加权（SPW）损失函数，能够高效生成自适应权重图。与依赖静态或迭代更新距离图的传统边界感知损失不同，我们的方法利用可操纵金字塔在多个频带上动态强调不同区域（捕获不同尺度特征），同时保持较低的计算开销。此外，通过将网络预测纳入权重计算，本方法能够在训练过程中实现自适应细化。我们在SNEMI3D、GlaS和DRIVE数据集上对所提方法进行了评估，并与11种最先进的损失函数进行了对比。实验结果表明，所提出的SPW损失函数在仅增加极小计算开销的情况下，取得了更优的像素精度和分割准确率。本工作为改进语义分割提供了一种有效且高效的解决方案，尤其适用于需要多尺度特征表示的应用场景。代码可在https://anonymous.4open.science/r/SPW-0884获取。
英文摘要：
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
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
