Timezone: »

Learnable Polyphase Sampling for Shift Invariant and Equivariant Convolutional Networks
Renan A. Rojas-Gomez · Teck-Yian Lim · Alex Schwing · Minh Do · Raymond A. Yeh

Tue Nov 29 02:00 PM -- 04:00 PM (PST) @ Hall J #912

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%.

Author Information

Renan A. Rojas-Gomez (University of Illinois at Urbana-Champaign)
Teck-Yian Lim (DSO National Laboratories)
Alex Schwing (University of Illinois at Urbana-Champaign)
Minh Do (University of Illinois)
Raymond A. Yeh (Purdue University)

More from the Same Authors