Abstract | ||
---|---|---|
Pruning is one of the most effective model reduction techniques. Deep networks require massive computation and such models need to be compressed to bring them on edge devices. Most existing pruning techniques are focused on vision-based models like convolutional networks, while text-based models are still evolving. The emergence of multi-modal multi-task learning calls for a general method that works on vision and text architectures simultaneously. We introduce a differentiable mask, that induces sparsity on various granularity to fill this gap. We apply our method successfully to prune weights, filters, subnetwork of a convolutional architecture, as well as nodes of a recurrent network. |
Year | DOI | Venue |
---|---|---|
2020 | 10.1109/CRV50864.2020.00037 | 2020 17th Conference on Computer and Robot Vision (CRV) |
Keywords | DocType | ISBN |
differentiable mask,pruning convolutional networks,recurrent networks,model reduction techniques,deep networks,edge devices,vision-based models,text-based models,multimodal multitask learning calls,text architectures,convolutional architecture,pruning techniques | Conference | 978-1-7281-9892-7 |
Citations | PageRank | References |
0 | 0.34 | 4 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Ramchalam Kinattinkara Ramakrishnan | 1 | 0 | 0.34 |
Eyyüb Sari | 2 | 0 | 0.34 |
Vahid Partovi Nia | 3 | 4 | 4.43 |