Phase Selective Convolution

Jamie Menjay Lin, Parham Noorzad, Yang Yang, Nojun Kwak, Fatih Porikli; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2021, pp. 3199-3208


This paper introduces Phase Selective Convolution (PSC), an enhanced convolution for more deliberate utilization of activations in convolutional networks. Unlike conventional use of convolutions with activation functions, PSC preserves the full space of activations while supporting desirable model nonlinearity. Similar to several other network operations, e.g., the ReLU operation, at the time of their introduction, PSC may not execute as efficiently on platforms without hardware specialization support. As a first step in addressing the need for optimization, we propose a hardware acceleration scheme to enable the intended efficiency for PSC execution. Moreover, we propose a PSC deployment strategy, with which PSC is applied only to selected layers of the networks, to avoid excessive increase in the total model size. To evaluate the results, we apply PSC as a drop-in replacement for selected convolution layers in several networks without affecting their macro network architectures. In particular, PSC-enhanced ResNets achieve higher accuracies by 1.0-2.0% and 0.7-1.0% on CIFAR-100 and ImageNet, respectively, in Pareto efficiency. PSC-enhanced MobileNets (V2 and V3 Large) and MobileNetV3 (Small) achieve 0.9-1.0% and 1.8% accuracy gains, respectively, on ImageNet at little (0.2-0.7%) total model size increase.

Related Material

[pdf] [supp]
@InProceedings{Lin_2021_CVPR, author = {Lin, Jamie Menjay and Noorzad, Parham and Yang, Yang and Kwak, Nojun and Porikli, Fatih}, title = {Phase Selective Convolution}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2021}, pages = {3199-3208} }