Context-Gated Convolution
By Xudong Lin, Lin Ma, Shih-Fu Chang. 2019
73 citations recorded by the source corpus.
As the basic building block of Convolutional Neural Networks (CNNs), the convolutional layer is designed to extract local patterns and lacks the ability to model global context in its nature. Many efforts have been recently devoted to complementing CNNs with the global modeling ability, especially by a family of works on global feature interaction. In these works, the global context information is incorporated into local features before they are fed into convolutional layers. However, research on neuroscience reveals that the neurons' ability of modifying their functions dynamically according to context is essential for the perceptual tasks, which has been overlooked in most of CNNs. Motivated by this, we propose one novel Context-Gated Convolution (CGC) to explicitly modify the weights of convolutional layers adaptively under the guidance of global context. As such, being aware of the global context, the modulated convolution kernel of our proposed CGC can better extract representative local patterns and compose discriminative features. Moreover, our proposed CGC is lightweight and applicable with modern CNN architectures, and consistently improves the performance of CNNs according to extensive experiments on image classification, action recognition, and machine translation. Our code of this paper is available at https://github.com/XudongLinthu/context-gated-convolution.
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
- Andrew Zisserman
- Cordelia Schmid
- João Carreira
- Lorenzo Torresani
- Quoc V. Le
- Mohit Bansal
- Trevor Darrell
- Christoph Feichtenhofer
In Computer Vision and Pattern Recognition
- Luc Van Gool
- Andrew Zisserman
- Dacheng Tao
- Jitendra Malik
- Xiaogang Wang
- Trevor Darrell
- Ming-Hsuan Yang
- Yi Yang
In Model Architectures
- Anbang Yao
- Oriol Vinyals
- Andrew Brock
- Yoshua Bengio
- João Carreira
- Andrew Zisserman
- Andrew Jaegle
- Aojun Zhou
Citations in the corpus
- Perceiver: General Perception with Iterative Attention (2021, background): “Re-entrant processing of this kind (sometimes referred to as top-down processing) has a long history in computer vision (Borenstein et al., 2004; Kumar et al., 2005; Carreira et al., 2016; Hu & Ramanan, 2016; Yang et al., 2018; Lin et al., 2020).”
- Omni-Dimensional Dynamic Convolution (2022, methodology): “ODConv also shows better recognition performance under similar model complexities when compared to other state-of-the-art attention methods for output feature recalibration (Woo et al., 2018; Hu et al., 2018b; Wang et al., 2020; Lin et al., 2020) or for convolutional weight modification (Ma et al.”