Phase-Aware Wavelet-Based-Scattering Encoder-Decoder for Dense Predictions

arXiv:2605.24621v1 Announce Type: cross Abstract: 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 +2.17dB; phase preservation adds +1.03dB. 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.

Source: arXiv cs.AI | 2026-05-26