Integrating Multiple Receptive Fields through Grouped Active Convolution

Abstract

Convolutional networks have achieved great success in various vision tasks. This is mainly due to a considerable amount of research on network structure. In this study, instead of focusing on architectures, we focused on the convolution unit itself. The existing convolution unit has a fixed shape and is limited to observing restricted receptive fields. In earlier work, we proposed the active convolution unit (ACU), which can freely define its shape and learn by itself. In this paper, we provide a detailed analysis of the previously proposed unit and show that it is an efficient representation of a sparse weight convolution. Furthermore, we extend an ACU to a grouped ACU, which can observe multiple receptive fields in one layer. We found that the performance of a naive grouped convolution is degraded by increasing the number of groups; however, the proposed unit retains the accuracy even though the number of parameters decreases. Based on this result, we suggest a depthwise ACU, and various experiments have shown that our unit is efficient and can replace the existing convolutions.

References in corpus (10)

• MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
• Rethinking Atrous Convolution for Semantic Image Segmentation
• Caffe: Convolutional Architecture for Fast Feature Embedding
• Neural Architecture Search with Reinforcement Learning
• Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition
• MobileNetV2: Inverted Residuals and Linear Bottlenecks
• Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)
• Wide Residual Networks
• Fractional Max-Pooling
• Oriented Response Networks