Imperial College London > Talks@ee.imperial > CAS Talks > Exploring spatial sparsity for more efficient CNNs in semantic segmentation
Log inImperial users Other users No account?Information onFinding a talk Adding a talk Syndicating talks Who we are Everything else |
Exploring spatial sparsity for more efficient CNNs in semantic segmentationAdd to your list(s) Download to your calendar using vCal
If you have a question about this talk, please contact George A Constantinides. CNNs demonstrate state-of-the art performance in most computer vision tasks. However, their improved performance comes with increased computational cost, limiting their adoption and usage in practical applications. To address that, we explore a flexible optimization scheme, which introduces spatial sparsity to a CNN to produce more efficient distribution of calculations. In this seminar, we will discuss how spatial sparsity can be introduced to a CNN and how it affects its performance. Moreover, we will also investigate the sparsity-based optimization scheme and how it can include actual latency to adapt to a target device. This talk is part of the CAS Talks series. This talk is included in these lists:
Note that ex-directory lists are not shown. |
Other listsSpatialML Seminar Series CBD and Its Medical Use in France: A Story of Relief and Wellness AI- and HCI-related talksOther talksKeynote Speech on Influence and persuasion Two Applications of Compression in Group Testing and Multi-Armed Bandits |