The reviewed record of science sign in
Pith

arxiv: 1907.09665 · v10 · pith:JLOLBI6M · submitted 2019-07-23 · cs.CV

Compact Global Descriptor for Neural Networks

Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:JLOLBI6Mrecord.jsonopen to challenge →

classification cs.CV
keywords globaldescriptorlong-rangemodelingaccessacrossavailablebenchmark
0
0 comments X
read the original abstract

Long-range dependencies modeling, widely used in capturing spatiotemporal correlation, has shown to be effective in CNN dominated computer vision tasks. Yet neither stacks of convolutional operations to enlarge receptive fields nor recent nonlocal modules is computationally efficient. In this paper, we present a generic family of lightweight global descriptors for modeling the interactions between positions across different dimensions (e.g., channels, frames). This descriptor enables subsequent convolutions to access the informative global features with negligible computational complexity and parameters. Benchmark experiments show that the proposed method can complete state-of-the-art long-range mechanisms with a significant reduction in extra computing cost. Code available at https://github.com/HolmesShuan/Compact-Global-Descriptor.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.