Latest from Purdue and Chicago researchers: Low-Power Object Counting! For proj
Deep Learning/resources 2020. 7. 10. 10:19Latest from Purdue and Chicago researchers: Low-Power Object Counting!
For project and code/API/dataset requests: https://www.catalyzex.com/paper/arxiv:2007.01369
By using a few small DNNs to process each image, this method reduces the memory requirement, inference time, energy consumption, and number of operations with negligible accuracy loss when compared with the existing object counters.
