Kernelized Classification in Deep Networks

8 Dec 2020  ·  Sadeep Jayasumana, Srikumar Ramalingam, Sanjiv Kumar ·

We propose a kernelized classification layer for deep networks. Although conventional deep networks introduce an abundance of nonlinearity for representation (feature) learning, they almost universally use a linear classifier on the learned feature vectors. We advocate a nonlinear classification layer by using the kernel trick on the softmax cross-entropy loss function during training and the scorer function during testing. However, the choice of the kernel remains a challenge. To tackle this, we theoretically show the possibility of optimizing over all possible positive definite kernels applicable to our problem setting. This theory is then used to device a new kernelized classification layer that learns the optimal kernel function for a given problem automatically within the deep network itself. We show the usefulness of the proposed nonlinear classification layer on several datasets and tasks.

PDF Abstract

Results from the Paper


  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.

Methods