通过频域滤波提升跨域少样本分割性能，效果显著且模型轻量。
Lightweight Frequency Masker for Cross-Domain Few-Shot Semantic Segmentation
- 在目标域图像上滤除特定频率成分，有效缓解域间差异影响。
- 最高提升14% mIoU，平均性能提升超10%，优于现有方法。
- 仅增加0.01%参数，适合资源受限场景下的高效部署。
跨域少样本语义分割（CD-FSS）先在大规模源域数据集上预训练模型，再迁移到数据稀缺的目标域进行像素级分割。源域与目标域间显著的域差异导致现有少样本分割方法性能急剧下降。本文发现：仅对目标域图像进行不同频率成分的滤波，即可带来显著性能提升，最高达14% mIoU。深入分析表明，该提升源于特征图中通道间相关性降低，增强了模型对域差异的鲁棒性，并扩大了分割激活区域。基于此，提出轻量级频率掩码器，包含幅度-相位掩码模块（APM）和自适应通道相位注意力模块（ACPA）。APM仅引入0.01%额外参数，平均性能提升超10%；ACPA引入2.5%参数，进一步提升超1.5%，显著超越当前最优CD-FSS方法。
原文摘要 · Abstract (English)
Cross-domain few-shot segmentation (CD-FSS) is proposed to first pre-train the model on a large-scale source-domain dataset, and then transfer the model to data-scarce target-domain datasets for pixel-level segmentation. The significant domain gap between the source and target datasets leads to a sharp decline in the performance of existing few-shot segmentation (FSS) methods in cross-domain scenarios. In this work, we discover an intriguing phenomenon: simply filtering different frequency components for target domains can lead to a significant performance improvement, sometimes even as high as 14% mIoU. Then, we delve into this phenomenon for an interpretation, and find such improvements stem from the reduced inter-channel correlation in feature maps, which benefits CD-FSS with enhanced robustness against domain gaps and larger activated regions for segmentation. Based on this, we propose a lightweight frequency masker, which further reduces channel correlations by an Amplitude-Phase Masker (APM) module and an Adaptive Channel Phase Attention (ACPA) module. Notably, APM introduces only 0.01% additional parameters but improves the average performance by over 10%, and ACPA imports only 2.5% parameters but further improves the performance by over 1.5%, which significantly surpasses the state-of-the-art CD-FSS methods.
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。