通过保留相位信息提升散射网络的像素级预测能力
Phase-Aware Wavelet-Based-Scattering Encoder-Decoder for Dense Predictions
- 在跳跃连接中显式保留相位，恢复被全局平均丢失的空间结构
- 图像去噪任务中相位保留使PSNR提升1.03dB，整体提升达2.17dB
- 首次验证相位编码位置依赖结构，适合关注细节的视觉任务
散射变换具备利普希茨稳定性与平移不变性，但密集预测任务需保留因全局平均而损失的空间结构。本文提出相位感知散射编码器-解码器，通过在跳跃连接中显式保留相位信息来恢复该结构。在图像去噪（BSD68）任务中，打破平移不变性使PSNR提升+2.17 dB；相位保留进一步带来+1.03 dB增益。一项新的空间打乱消融实验显示-1.26 dB性能下降，证明相位编码了位置相关结构。初步扩展研究在另一密集预测任务（ISIC皮肤病变分割）上进行，完整交叉验证仍在进行中。本工作推进了小波与深度学习的原理性融合，揭示了相位信息如何在像素级预测中调和散射变换的稳定性与表达力之间的权衡。
原文摘要 · Abstract (English)
Scattering transforms achieve Lipschitz stability and translation invariance, but dense prediction tasks require preserving spatial structure lost in global averaging. We propose Phase-Aware Scattering Encoder-Decoder, which restores this information by explicitly preserving phase in skip connections. On image denoising (BSD68), breaking translation invariance improves PSNR by $+2.17$~dB; phase preservation adds $+1.03$~dB. A novel spatial shuffling ablation ($-1.26$~dB penalty) demonstrates phase encodes location-dependent structure. We conduct a preliminary extensibility study on a second dense prediction task (ISIC skin lesion segmentation), with full cross-validation as ongoing work. This work advances principled wavelet-deep learning integration, showing how phase information complements scattering's stability-expressiveness trade-off in pixel-level prediction.
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。