Global Context Networks
Citations Over TimeTop 10% of 2020 papers
Abstract
The non-local network (NLNet) presents a pioneering approach for capturing long-range dependencies within an image, via aggregating query-specific global context to each query position. However, through a rigorous empirical analysis, we have found that the global contexts modeled by the non-local network are almost the same for different query positions. In this paper, we take advantage of this finding to create a simplified network based on a query-independent formulation, which maintains the accuracy of NLNet but with significantly less computation. We further replace the one-layer transformation function of the non-local block by a two-layer bottleneck, which further reduces the parameter number considerably. The resulting network element, called the global context (GC) block, effectively models global context in a lightweight manner, allowing it to be applied at multiple layers of a backbone network to form a global context network (GCNet). Experiments show that GCNet generally outperforms NLNet on major benchmarks for various recognition tasks. The code and network configurations are available at https://github.com/xvjiarui/GCNet.
Related Papers
- A Placement Algorithm of Content Distribution Network(CDN)(2004)
- → Research on the Bottleneck Area of Optimal BGP Route Selection(2005)3 cited
- Research on Video-on-Demand System Model and Algorithm Based on P2P(2006)
- Continuous Query Based on Streaming Data Technology(2005)
- Research on Mobile Sink of Wireless Sensor Network(2007)