AI Paper Atlas

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

Human-in-the-Loop Feature Selection

Alvaro H. C. Correia, Freddy Lecue

AAAI 2019 · Label-efficient and robust learning › Recognition and long-tail · approach: Prototype and concept dictionary models · 26 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
add simulated human feature feedback (SF, cosine) (ablation)per-example feature selection · Cluttered MNIST 60x60accuracy (%): 85.35 -> 92.30Improved
add real expert feature feedback (SF, cosine) (ablation)per-example feature selection · Project Risk Classificationaccuracy (%): 29.53 -> 82.49Improved
use SF instead of PD estimator (ablation)feedback-based selection · Project Risk Classificationaccuracy (%): 77.51 -> 82.49Improved
use SF instead of PD estimator (ablation)feedback-based selection · Cluttered MNIST 60x60accuracy (%): 88.40 -> 92.30Improved
set Gumbel-softmax temperature to 1.0 vs other values (ablation)PD estimator · Project Risk Classificationaccuracy (%): 77.82 -> 81.87Improved
increase number of states K from 2 to 8 (ablation)PD estimator · Project Risk Classificationaccuracy (%): 73.11 -> 79.44Mixed
increase number of states K from 2 to 20 (ablation)PD estimator · Cluttered MNISTaccuracy (%): 89.50 -> 85.40Hurt
start feedback later (epoch 40 vs 80) (ablation)SF with MSE feedback · Project Risk Classificationaccuracy (%): 80.11 -> 52.10Hurt
remove all conflicting feedback (ablation)SF with MSE feedback · Project Risk Classificationaccuracy (%): 86.67 -> 69.87Hurt
increase feedback amount from 50% to 100% (ablation)SF with MSE feedback · Project Risk Classificationaccuracy (%): 61.65 -> 80.11Improved
MSE vs cosine dissimilarity (ablation)feedback loss · Project Risk Classificationaccuracy (%): 82.49 vs 80.11No clear effect

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