AI Paper Atlas

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

Species Distribution Modeling of Citizen Science Data as a Classification Problem with Class-Conditional Noise

Rebecca Hutchinson, Liqiang He, Sarah Emerson

AAAI 2017 · Label-efficient and robust learning › Recognition and long-tail · approach: Group-robust classification · 7 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
use FP (false-positive and false-negative noise features) model instead of LR1, LR2, OCC or CNclass-conditional noise model · simulated data #1-7, 3200 instancesMSE of class probabilitiesImproved
misspecify the link function (probit or scale) in data generation while fitting with logitFP model · simulated datasets #8-9MSE of class probabilitiesHurt
reduce training set sizeFP model · dataset #1MSE of class probabilitiesHurt
CN model without feature functions for noise (non-identifiable noise parameters)CN model · simulated dataMSE of class probabilitiesHurt
vary feature type and overlap between feature functionsFP model · simulated data #1-7MSE of class probabilitiesNo clear effect
larger training set (California about twice New York)FP models · Sim2 eBirdMSE vs OCC and CNImproved
selected FP model vs CN model on simulated speciesFP model · Sim1 eBird test setMSE on psi, rho, etaImproved

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