AI Paper Atlas

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

Generalized One-Class Learning Using Pairs of Complementary Classifiers

Anoop Cherian, Jue Wang

TPAMI 2021 · Label-efficient and robust learning › Recognition and long-tail · approach: Learning from unlabeled and positive-unlabeled data · 8 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 L2 unit normalization of input features (ablation)GODS · JHMDBF1 (%): 75.2 -> 77.7Improved
add L2 unit normalization of input features (ablation)GODS · UCF-CrimeAUC (%): 68.9 -> 70.0Improved
add L2 unit normalization of input features (ablation)GODS · Dash-Cam-Pose (TCN)F1bar (%): 56.6 -> 58.4Improved
add L2 unit normalization of input features (ablation)GODS_E (Euclidean) · UCF-CrimeAUC (%): 64.6 -> 66.8Improved
add soft-orthogonality penalty C with L2 normalization (ablation)GODS · JHMDBF1 (%): 77.7 -> 77.5No clear effect
add soft-orthogonality penalty C with L2 normalization (ablation)GODS · UCF-CrimeAUC (%): 70.0 -> 70.3No clear effect
use Stiefel manifold instead of non-compact Stiefel (ablation)GODS · UCF-CrimeAUC (%): 68.6 -> 70.0Improved
use Stiefel manifold instead of Euclidean manifold (ablation)GODS · UCF-CrimeAUC (%): 66.8 -> 70.0Improved
use Stiefel manifold instead of oblique manifold (ablation)GODS · UCF-CrimeAUC (%): 66.7 -> 70.0Improved
use Stiefel manifold instead of Euclidean manifold (ablation)GODS · Dash-Cam-Pose (TCN)F1bar (%): 55.8 -> 58.4Improved
use multiple orthonormal hyperplanes (GODS) instead of a single hyperplane pair (BODS)GODS · JHMDBF1: 0.725 -> 0.777Improved
use kernelized KODS instead of GODSKODS · Dash-Cam-Pose (TCN)F1bar: 0.584 -> 0.664Improved

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