Back to Search
Start Over
Learnable Polyphase Sampling for Shift Invariant and Equivariant Convolutional Networks
- Publication Year :
- 2022
-
Abstract
- We propose learnable polyphase sampling (LPS), a pair of learnable down/upsampling layers that enable truly shift-invariant and equivariant convolutional networks. LPS can be trained end-to-end from data and generalizes existing handcrafted downsampling layers. It is widely applicable as it can be integrated into any convolutional network by replacing down/upsampling layers. We evaluate LPS on image classification and semantic segmentation. Experiments show that LPS is on-par with or outperforms existing methods in both performance and shift consistency. For the first time, we achieve true shift-equivariance on semantic segmentation (PASCAL VOC), i.e., 100% shift consistency, outperforming baselines by an absolute 3.3%.<br />Comment: Accepted at the Thirty-sixth Conference on Neural Information Processing Systems (NeurIPS 2022)
Details
- Database :
- arXiv
- Publication Type :
- Report
- Accession number :
- edsarx.2210.08001
- Document Type :
- Working Paper