CTech – The International Conference on Machine Learning (ICML) today presented the Outstanding Paper Award to a group of Israeli researchers and professors. It describes the award as given to papers that “are strong representatives of solid theoretical and empirical work in our field.”
“On Learning Sets of Symmetric Elements” was led by Hagai Meron from NVIDIA’s research group in Israel, with Or Litani from Stanford University, Ethan Fetaya of Bar Ilan University, Professor Gal Chechik of Bar Ilan University, and the director of the NVIDIA Research Group in Israel.
In the paper, they introduced an approach to learning sets of general symmetric elements that could be used in a variety of ways, including deblurring images, 3D shape recognition, and reconstruction.
“Our research proves theoretically what deep neural network architectures should be used when learning across sets of complex objects, where by complex we mean that the objects assume a special structure which we refer to as symmetry. We also show empirically that this architecture achieves superior results in a range of problems over images, graphs, and 3D point clouds,” the paper read.
It concludes by stating that their architectures can be used to reduce noise and identify action highlights given a set of images. All experiments were conducted using NVIDIA DGX systems with NVIDIA V100 GPUs.
2020 marked the 37th International Conference on Machine Learning. Unlike other years, the entire conference was held online due to Covid-19 restrictions. Its official venue was Vienna, Austria.
Credit: Google News