AI Paper Atlas

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

AdaFlock: Adaptive Feature Discovery for Human-in-the-loop Predictive Modeling

Ryusuke Takahama, Yukino Baba, Nobuyuki Shimizu, Sumio Fujita, Hisashi Kashima

AAAI 2018 · Label-efficient and robust learning › Recognition and long-tail · approach: Dense features and foundation priors · 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
adaptive example selection for feature definition (AdaFlock vs StandardFlock) (ablation)feature crowdsourcing · Paintings trial 1testing accuracy: 0.755 -> 0.820Improved
adaptive example selection for feature definition (AdaFlock vs StandardFlock) (ablation)feature crowdsourcing · Paintings trial 2testing accuracy: 0.745 -> 0.705Hurt
adaptive example selection (AdaFlock vs StandardFlock) (ablation)feature crowdsourcing · Smiles trial 1testing accuracy: 0.715 -> 0.780Improved
adaptive example selection (AdaFlock vs StandardFlock) (ablation)feature crowdsourcing · Smiles trial 2testing accuracy: 0.720 -> 0.740Improved
AdaFlock vs crowd predictionclassification · Paintings trial 1testing accuracy: 0.560 -> 0.820Improved
AdaFlock vs crowd predictionclassification · Paintings trial 2testing accuracy: 0.580 -> 0.705Improved
AdaFlock vs crowd predictionclassification · Smiles trial 1testing accuracy: 0.720 -> 0.780Improved
AdaFlock vs crowd predictionclassification · Smiles trial 2testing accuracy: 0.715 -> 0.740Improved
AdaFlock crowd features vs off-the-shelf Inception-v3 featuresclassification · Paintings trial 1testing accuracy: 0.755 -> 0.820Improved
AdaFlock crowd features vs off-the-shelf Inception-v3 featuresclassification · Paintings trial 2testing accuracy: 0.735 -> 0.705Hurt
increase AdaFlock iterations (feature discovery of ground feature at iteration 5)AdaFlock · Paintings trial 1testing accuracy: 10%Improved
increase AdaFlock iterations (discovery of short-duration feature)AdaFlock · Smilestesting accuracy: 8%Improved

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