Technology
USCILab3D: A Large-scale, Long-term, Semantically Annotated Outdoor Dataset
In this paper, we introduce the USCILab3D dataset, a large-scale, annotated outdoor dataset designed for versatile applications across multiple domains, including computer vision, robotics, and machine learning.
Efficient Rematerialization for Deep Networks
Ravi Kumar, Manish Purohit, Zoya Svitkina, Erik Vee, Joshua Wang
When training complex neural networks, memory usage can be an important bottleneck.
Fully Dynamic Consistent Facility Location
Vincent Cohen-Addad, Niklas Oskar D. Hjuler, Nikos Parotsidis, David Saulpic, Chris Schwiegelshohn
Neural Information Processing Systems http://nips.cc/
Modern Neural Networks Generalize on Small Data Sets
Matthew Olson, Abraham Wyner, Richard Berk
Neural Information Processing Systems http://nips.cc/
Equality of Opportunity in Classification: A Causal Approach
Junzhe Zhang, Elias Bareinboim
Despitethis noble goal, it has been acknowledged in the literature that statistical tests based ontheEOareoblivious totheunderlying causal mechanisms thatgenerated the disparity in the first place (Hardt et al. 2016).
Adaptively Aligned Image Captioning via Adaptive Attention Time
Lun Huang, Wenmin Wang, Yaxian Xia, Jie Chen
AATallowstheframeworktolearn howmany attention steps to take to output a caption word at each decoding step. With AAT, an image region can be mapped to an arbitrary number of caption words while a caption word can also attend to an arbitrary number of image regions. AAT is deterministic and differentiable, and doesn't introduce any noise to the parameter gradients.
Replicable Clustering
This means that the algorithm designer needs to balance several conflicting desiderata.
Discrete Object Generation with Reversible Inductive Construction
Ari Seff, Wenda Zhou, Farhan Damani, Abigail Doyle, Ryan P. Adams
Neural Information Processing Systems http://nips.cc/