提出复小波互信息损失，提升小目标和边界分割精度。
Complex Wavelet Mutual Information Loss: A Multi-Scale Loss Function for Semantic Segmentation
- 用复可旋转金字塔分解图像，提取多尺度方向特征
- 基于子带图的互信息计算，显著提升小物体和边界的分割效果
- 计算开销低，适合实际部署，尤其对细长结构敏感
深度神经网络在语义分割中表现优异，但类别不平衡和实例不平衡问题仍存在，小目标和细边界常被大结构掩盖。为应对多尺度分割挑战，现有模型引入空间注意力和特征金字塔等机制，但多数损失函数仍为像素级，区域与边界相关损失往往计算量大或仅适用于小范围。为此，本文提出复小波互信息（CWMI）损失，利用复可旋转金字塔对图像进行子带分解，捕捉多方向特征并保持跨尺度结构相似性；互信息能有效表征高维方向特征且具备强抗噪能力。在多个分割数据集上的实验表明，相较于当前最优方法，CWMI损失在像素级准确率和拓扑指标上均有显著提升，同时引入的计算开销极小。代码已公开于https://github.com/lurenhaothu/CWMI。
原文摘要 · Abstract (English)
Recent advancements in deep neural networks have significantly enhanced the performance of semantic segmentation. However, class imbalance and instance imbalance remain persistent challenges, where smaller instances and thin boundaries are often overshadowed by larger structures. To address the multiscale nature of segmented objects, various models have incorporated mechanisms such as spatial attention and feature pyramid networks. Despite these advancements, most loss functions are still primarily pixel-wise, while regional and boundary-focused loss functions often incur high computational costs or are restricted to small-scale regions. To address this limitation, we propose the complex wavelet mutual information (CWMI) loss, a novel loss function that leverages mutual information from subband images decomposed by a complex steerable pyramid. The complex steerable pyramid captures features across multiple orientations and preserves structural similarity across scales. Meanwhile, mutual information is well-suited to capturing high-dimensional directional features and offers greater noise robustness. Extensive experiments on diverse segmentation datasets demonstrate that CWMI loss achieves significant improvements in both pixel-wise accuracy and topological metrics compared to state-of-the-art methods, while introducing minimal computational overhead. Our code is available at https://github.com/lurenhaothu/CWMI
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。