AI Paper Atlas

Research map / Label-efficient and robust learning / OOD and anomaly detection

Gradient-Based Novelty Detection Boosted by Self-Supervised Binary Classification

Jingbo Sun, Li Yang, Jiaxin Zhang, Frank Liu, Mahantesh Halappanavar, Deliang Fan, Yu Cao

AAAI 2022 · Label-efficient and robust learning › OOD and anomaly detection · approach: Provable and feature-based OOD detection · 12 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
select an OOD gradient label to maximize Mahalanobis distance rather than use the predicted label (ablation)Gradient-based novelty detector · CIFAR-10 IDD / TinyImageNet, SVHN, LSUN, and CIFAR-100 OODAUROC: 91.10 -> 99.92; 91.63 -> 99.99; 90.08 -> 99.99; 86.03 -> 97.99Improved
add the self-supervised binary classifier to guide label selection (ablation)Gradient-based novelty detector · Four OOD test cases in the ablation studyAUROCImproved
train the binary classifier on detector-selected high- and low-score samples instead of randomly selected samples (ablation)Self-supervised binary classifier · OOD detection experimentsAUROCImproved
use fewer detector-selected IDD/OOD images to train the binary classifier (ablation)Self-supervised binary classifier · OOD detection experimentsAUROCHurt
re-initialize the binary classifier after each iteration (ablation)Self-supervised binary classifier · CIFAR-10 IDD / CIFAR-100 OODAUROCImproved
increase binary-classifier batch size from 8 to 32 or 128 (ablation)Proposed detector · CIFAR-10 IDD / CIFAR-100 OODAUROC: 84.79 -> 93.51 -> 97.99Improved
increase binary-classifier batch size from 8 to 32 or 128 (ablation)Proposed detector · CIFAR-100 IDD / CIFAR-10 OODAUROC: 72.61 -> 89.76 -> 91.38Improved
increase binary-classifier batch size (ablation)Proposed detector · Multiple IDD/OOD pairsAUROCMixed
use last-layer feature-extractor gradients with Mahalanobis distance instead of only feedforward featuresProposed novelty detector · OOD detectionAUROCImproved
train the binary classifier from detector-generated pseudo-labels rather than labeled OOD dataProposed novelty detector · OOD detectionAUROCImproved
use the proposed detector for one-class continual learning with a memory budget of 1,000CIFAR-10 9+1 single-head learning · CIFAR-10 new-class recognitionaccuracy: 91-96% accuracy in any classImproved

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