MABe22: A Multi-Species Multi-Task Benchmark for Learned Representations of Behavior

1 code implementation • 21 Jul 2022 • Jennifer J. Sun, Markus Marks, Andrew Ulmer, Dipam Chakraborty, Brian Geuther, Edward Hayes, Heng Jia, Vivek Kumar, Sebastian Oleszko, Zachary Partridge, Milan Peelman, Alice Robie, Catherine E. Schretter, Keith Sheppard, Chao Sun, Param Uttarwar, Julian M. Wagner, Eric Werner, Joseph Parker, Pietro Perona, Yisong Yue, Kristin Branson, Ann Kennedy

We introduce MABe22, a large-scale, multi-agent video and trajectory benchmark to assess the quality of learned behavior representations.

Pose Tracking Representation Learning +1

Understanding Classifier Errors by Examining Influential Neighbors

no code implementations • CVPR 2015 • Mayank Kabra, Alice Robie, Kristin Branson

As computing the influence of each training example is computationally impractical, we propose a novel distance metric to approximate influence for boosting classifiers that is fast enough to be used interactively.