A Weakly Supervised Approach for Estimating Spatial Density Functions from High-Resolution Satellite Imagery

1 code implementation • 22 Oct 2018 • Nathan Jacobs, Adam Kraft, Muhammad Usman Rafique, Ranti Dev Sharma

We propose a neural network component, the regional aggregation layer, that makes it possible to train a pixel-level density estimator using only coarse-grained density aggregates, which reflect the number of objects in an image region.

PyGlove: Symbolic Programming for Automated Machine Learning

no code implementations • NeurIPS 2020 • Daiyi Peng, Xuanyi Dong, Esteban Real, Mingxing Tan, Yifeng Lu, Hanxiao Liu, Gabriel Bender, Adam Kraft, Chen Liang, Quoc V. Le

As a result, AutoML can be reformulated as an automated process of symbolic manipulation.

AutoML BIG-bench Machine Learning