Learning to map between ferns with differentiable binary embedding networks
This work addresses computational efficiency for deep learning practitioners, though it is incremental as it builds on existing binary and fern-based methods.
The authors tackled the problem of expensive convolutions in deep learning by introducing differentiable random ferns as a multiplication-free alternative, achieving improved results over XNOR net and near-parity with a more parameter-intensive CNN on the TUPAC'16 binary classification task.
Current deep learning methods are based on the repeated, expensive application of convolutions with parameter-intensive weight matrices. In this work, we present a novel concept that enables the application of differentiable random ferns in end-to-end networks. It can then be used as multiplication-free convolutional layer alternative in deep network architectures. Our experiments on the binary classification task of the TUPAC'16 challenge demonstrate improved results over the state-of-the-art binary XNOR net and only slightly worse performance than its 2x more parameter intensive floating point CNN counterpart.