AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Bias Reduction via End-to-End Shift Learning: Application to Citizen Science

Di Chen, Carla P. Gomes

AAAI 2019 · Label-efficient and robust learning › Recognition and long-tail · approach: Data augmentation and generalization bias · 18 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
apply covariate-shift correction with SCN rather than train without bias correctionmulti-species distribution modeling · eBird, NLCD featuresAUC: 77.86 -> 80.34Improved
apply covariate-shift correction with SCN rather than train without bias correctionmulti-species distribution modeling · eBird, Google Earth imagesAUC: 80.93 -> 83.80Improved
use end-to-end SCN instead of the strongest listed baseline, DFWmulti-species distribution modeling · eBird, NLCD featuresAUC: 79.38 -> 80.34Improved
use end-to-end SCN instead of the strongest listed baseline, DFWmulti-species distribution modeling · eBird, Google Earth imagesAUC: 81.99 -> 83.80Improved
add feature space mean matching loss (ablation)SCN · eBird, NLCD featuresAUC: 79.53 -> 80.34Improved
add feature space mean matching loss (ablation)SCN · eBird, Google Earth imagesAUC: 82.35 -> 83.80Improved
add discriminative loss (ablation)SCN · eBird, NLCD featuresAUC: 79.58 -> 80.34Improved
add discriminative loss (ablation)SCN · eBird, Google Earth imagesAUC: 82.49 -> 83.80Improved
use moving-average rather than batch-wise estimation for FSMM (ablation)SCN · eBird, NLCD featuresAUC: 80.09 -> 80.34Improved
use moving-average rather than batch-wise estimation for FSMM (ablation)SCN · eBird, Google Earth imagesAUC: 83.44 -> 83.80Improved
use FSMM alone to learn the shift factor, without the discriminative loss (ablation)SCN · eBird multi-species modelingpredictive performanceMixed

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy