2265 results for "earn" across all locations
Ride from Newark Airport for 50% Less
We’ve dropped uberX and uberXL fares from Newark Airport by an average of 50%. Get the full details.
Mabrook! Women Take the Wheel in Saudi Arabia
On June 24, 2018, Saudi women will be able to drive in their country for the first time in history. We’re celebrating with them.
Mabrook! Women Take the Wheel in Saudi Arabia
On June 24, 2018, Saudi women will be able to drive in their country for the first time in history. We’re celebrating with them.
Celebrating Saudi National Day
Meet Joseph, our first Seahawks All Star Driver
We’re lucky to have stellar driver-partners who help keep the city in motion. To celebrate our first All Star Driver of the season, we’re recognizing
Electrifying for a greener Portland
Uber is working together with Forth and PGE in Portland around electric vehicles as part of our commitment to a more sustainable future
Meet Sergio, our latest All Star Driver
We’re continuing to celebrate amazing drivers who help keep Seattle moving. Our All Star Driver Sergio, his wife, and 3 daughters enjoyed the ultimate
The Next Generation of Women Engineers
The next generation of engineers and coders are brimming with ideas for new apps, competitive startups, and social good concepts. This week, Uber’s New York City office hosted a group of aspiring young women entrepreneurs and heard their well-prepared pitches for apps relating to food, safety, news, transportation, and education.
DMM-Net: Differentiable Mask-Matching Network for Video Instance Segmentation
X. Zeng, R. Liao, L. Gu, Y. Xiong, S. Fidler, R. Urtasun
We propose the differentiable mask-matching network (DMM-Net) for solving the video instance segmentation problem where the initial instance masks are provided. On DAVIS 2017 dataset, DMM-Net achieves the best performance without online learning on the first frames and the 2nd best with it. Without any fine-tuning, DMM-Net performs comparably to state-of-the-art methods on SegTrack v2 dataset. [PDF]
International Conference on Computer Vision (ICCV), 2019
LCA: Loss Change Allocation for Neural Network Training
J. Lan, R. Liu, H. Zhou, J. Yosinski
Neural networks enjoy widespread use, but many aspects of their training, representation, and operation are poorly understood. In particular, our view into the training process is limited, with a single scalar loss being the most common viewport into this high-dimensional, dynamic process. We propose a new window into training called Loss Change Allocation (LCA), in which credit for changes to the network loss is conservatively partitioned to the parameters. […] [PDF]
Conference on Neural Information Processing Systems (NeurIPS), 2019