Exploiting Activation based Gradient Output Sparsity to Accelerate Backpropagation in CNNs

no code implementations • 16 Sep 2021 • Anup Sarma, Sonali Singh, Huaipan Jiang, Ashutosh Pattnaik, Asit K Mishra, Vijaykrishnan Narayanan, Mahmut T Kandemir, Chita R Das

By exploiting sparsity in both the forward and backward passes, speedup improvements range from 1. 68$\times$ to 3. 30$\times$ over the sparsity-agnostic baseline execution.

Image Classification object-detection +1