Full Characterization of Adaptively Strong Majority Voting in Crowdsourcing

no code implementations • 11 Nov 2021 • Margarita Boyarskaya, Panos Ipeirotis

Using these results, we show further that one can adapt the value of the threshold {\delta} to achieve quality-equivalence across voting processes that employ workers of different accuracy levels.

Building a Bird Recognition App and Large Scale Dataset With Citizen Scientists: The Fine Print in Fine-Grained Dataset Collection

no code implementations • CVPR 2015 • Grant Van Horn, Steve Branson, Ryan Farrell, Scott Haber, Jessie Barry, Panos Ipeirotis, Pietro Perona, Serge Belongie

We worked with bird experts to measure the quality of popular datasets like CUB-200-2011 and ImageNet and found class label error rates of at least 4%.