Dynamic Region-Aware Convolution

By Jin Chen, Xijun Wang, Zichao Guo, X. Zhang, Jian‐Yuan Sun. 2020

139 citations recorded by the source corpus.

We propose a new convolution called Dynamic Region-Aware Convolution (DRConv), which can automatically assign multiple filters to corresponding spatial regions where features have similar representation. In this way, DR-Conv outperforms standard convolution in modeling semantic variations. Standard convolutional layer can increase the number of filers to extract more visual elements but results in high computational cost. More gracefully, our DR-Conv transfers the increasing channel-wise filters to spatial dimension with learnable instructor, which not only improve representation ability of convolution, but also maintains computational cost and the translation-invariance as standard convolution dose. DRConv is an effective and elegant method for handling complex and variable spatial information distribution. It can substitute standard convolution in any existing networks for its plug-and-play property, especially to power convolution layers in efficient networks. We evaluate DRConv on a wide range of models (MobileNet series, ShuffleNetV2, etc.) and tasks (Classification, Face Recognition, Detection and Segmentation). On ImageNet classification, DRConv-based ShuffleNetV2-0.5 achieves state-of-the-art performance of 67.1% at 46M× multiply-adds level with 6.3% relative improvement.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Model Architectures

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Lu Yuan
2. Tao Mei
3. Shiji Song
4. Yingwei Pan
5. Gao Huang
6. Yehao Li
7. Xiyang Dai
8. Yulin Wang

In Computer Vision and Pattern Recognition

1. Luc Van Gool
2. Dacheng Tao
3. Lu Yuan
4. Jianfeng Gao
5. Tao Mei
6. Ming-Hsuan Yang
7. Xiaogang Wang
8. Trevor Darrell

In Model Architectures

1. Lu Yuan
2. Xiyang Dai
3. Dongdong Chen
4. Zicheng Liu
5. Shiji Song
6. Yinpeng Chen
7. Mengchen Liu
8. Gao Huang

Citations in the corpus

• Dynamic Neural Networks: A Survey (2021, background): “identical weights, dynamic region-aware convolution (DRConv) [155] generates a segmentation mask for an input image, dividing it into m regions, for each of which a weight generation network is responsible for producing a data-dependent kernel.”
• Contextual Transformer Networks for Visual Recognition (2021, background): “Nevertheless, the filter generator module in [6] produces the specialized filters based on the primary input feature map.”
• Revisiting Dynamic Convolution via Matrix Decomposition (2021, background): “Chen et al. (2020b) extends dynamic convolution from spatial agnostic to spatial specific.”