Description
Big-Little Modules are blocks for image models that have two branches: each of which represents a separate block from a deep model and a less deep counterpart. They were proposed as part of the BigLittle-Net architecture. The two branches are fused with a linear combination and unit weights. These two branches are known as Big-Branch (more layers and channels at low resolutions) and Little-Branch (fewer layers and channels at high resolution).
Papers Using This Method
Large Scale Neural Architecture Search with Polyharmonic Splines2020-11-20WaveGrad: Estimating Gradients for Waveform Generation2020-09-02Compounding the Performance Improvements of Assembled Techniques in a Convolutional Neural Network2020-01-17Big-Little Net: An Efficient Multi-Scale Feature Representation for Visual and Speech Recognition2018-07-10