Senior Research Scientist @intel. Before @facebook and @pixar, PhD@Purdue, volunteer at life. Also, nerd in CV/graphics, Krobelus@Dota, bachatera on stage.
Nov 14, 2020 • 8 tweets • 4 min read
Are you trying to visualize your deep network just 2 days before the #CVPR2021 deadline? Here are some pretty alternatives to boring tensorboard graphs. (1/n)
Tensorspace: tensorspace.org
Fun, interactive, 3D, and you can zoom into a specific layer for samples. (2/n)
Jun 19, 2020 • 8 tweets • 5 min read
Last day of the main conference at #CVPR2020, and here are my non-scientifically chosen top five papers @CVPR for the last day. Visit them in the next 10(?) hours! (1/6)
1. High-Dimensional Convolutional Networks for Geometric Pattern Recognition
Authors: Christopher Choy, Junha Lee, René Ranftl, Jaesik Park, Vladlen Koltun
Correspondences in 2D/3D forms geometric structures in higher dim, let's segment those with ND convnets!
For the night session attendees of #CVPR2020, here is my completely non-scientifically chosen top five papers @cvpr for the second day. Visit them in the next 8 hours! (1/6)
1. DualConvMesh-Net: Joint Geodesic and Euclidean Convolutions on 3D Meshes
Authors: Jonas Schult, Francis Engelmann, Theodora Kontogianni, Bastian Leibe
Conv->(euclidean+geodesic) convs
Pooling->mesh simplification
6% mIoU increase and a nice paper!
For the night session attendees of #CVPR2020, here is my completely non-scientifically chosen top five papers @cvpr first day. Visit them in the next 8 hours! (1/6)
1. Perspective Plane Program Induction From a Single Image
Authors: Yikai Li, Jiayuan Mao, Xiuming Zhang, William T. Freeman, Joshua B. Tenenbaum, Jiajun Wu @MIT_CSAIL
Domain agnostic image-based proceduralization with single terminal and grid-based rules.
