Learnable Polyphase Sampling for Shift Invariant and Equivariant Convolutional Networks
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%.
Code (1)
Tasks
image-classificationImage ClassificationSegmentationSemantic SegmentationSimilar Papers 제목 키워드 기반
Truly shift-equivariant convolutional neural networks with adaptive polyphase upsampling
Convolutional neural networks lack shift equivariance due to the presence of downsampling layers. In image classification, adaptive polyphase downsampling (APS-D) was recently proposed to make CNNs perfectly shift invari…
CT ReconstructionData AugmentationDecoderimage-classification+2Improving Shift Invariance in Convolutional Neural Networks with Translation Invariant Polyphase Sampling
Downsampling operators break the shift invariance of convolutional neural networks (CNNs) and this affects the robustness of features learned by CNNs when dealing with even small pixel-level shift. Through a large-scale …
image-classificationImage ClassificationSemantic SegmentationTranslationShift-Equivariant Complex-Valued Convolutional Neural Networks
Convolutional neural networks have shown remarkable performance in recent years on various computer vision problems. However, the traditional convolutional neural network architecture lacks a critical property: shift equ…
Semantic SegmentationData AugmentationTruly shift-invariant convolutional neural networks
Thanks to the use of convolution and pooling layers, convolutional neural networks were for a long time thought to be shift-invariant. However, recent works have shown that the output of a CNN can change significantly wi…
Data AugmentationReviving Shift Equivariance in Vision Transformers
Shift equivariance is a fundamental principle that governs how we perceive the world - our recognition of an object remains invariant with respect to shifts. Transformers have gained immense popularity due to their effec…
Inductive Bias