arXiv：cs.LG· Wei Wu, Eric C. Larson·· 3 小时前
可学习缩放与谱域滤波器参数化下的分辨率分配研究
Resolution Allocation with Learnable Resizing and Spectral Filter Parameterization
AI 导读
研究系统对比了空间域与谱域卷积核在可学习下采样比例下的表现，在 EuroSAT、CIFAR-10 和 STL-10 三个数据集及两种模型规模上，谱域卷积核的准确率增益比空间域高 +0.013 至 +0.028。部分差异源于谱域核从保留更大空间面积中获益更多，但在总保留面积匹配时差异仍为正。该模式随模型规模和缩放实现方式而变化。
正文
Abstract:Learnable downsampling and spectral-domain filter parameterizations have each made convolutional networks more flexible, but their interaction has not been systematically examined. We bridge this gap by examining convolutional kernels learned in the spatial and spectral domains, together with learned downsampling ratios under a cropped resizing implementation. We find that spectral and spatial kernels respond differently to learned resolution allocation, with larger gains for the spectral kernel. We observe this consistently on three datasets (EuroSAT, CIFAR-10 and STL-10) and at two model sizes (differences in accuracy gain of +0.013 to +0.028 on held-out test sets). Part of this difference reflects the greater gain of the spectral kernel from retaining more spatial area, but the difference remains positive when total retained area is matched. This pattern is observed across datasets and model sizes, although its magnitude and dependence on the complexity budget vary with model size and the resizing implementation.
| Comments: | 5 pages, 3 figures, 2 tables. Submitted to ICASSP 2027 |
| Subjects: | Machine Learning (cs.LG); Computer Vision and Pattern Recognition (cs.CV) |
| Cite as: | arXiv:2610.20274 [cs.LG] |
| (or arXiv:2610.20274v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.20274 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Wei Wu [view email]
[v1]
Wed, 14 Oct 2026 14:35:28 UTC (64 KB)
来源：arXiv：cs.LG · arxiv.org