AI Paper Atlas

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

GradOrth: A Simple yet Efficient Out-of-Distribution Detection with Orthogonal Projection of Gradients

Sima Behpour, Thang Doan, Xin Li, Wenbin He, Liang Gou, Liu Ren

NeurIPS 2023 · Label-efficient and robust learning › OOD and anomaly detection · approach: Spurious-aware OOD detection · 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 last layer instead of all layers (ablation)GradOrth · ImageNet ResNet-50avg FPR95: 20.35 -> 18.57Improved
use last layer instead of all layers (ablation)GradOrth · ImageNet MobileNetV2avg FPR95: 29.17 -> 27.65Improved
use last layer instead of all layers (ablation)GradOrth · CIFAR-10avg FPR95: 13.16 -> 12.34Improved
use last layer instead of all layers (ablation)GradOrth · CIFAR-100avg FPR95: 34.84 -> 33.35Improved
use last layer instead of all layers (ablation)GradOrth · ImageNet MobileNetV2 iNaturalistFPR95: 26.14 -> 26.81Hurt
increase samples per class for subspace from 5 to 10 (ablation)GradOrth · CIFAR-10avg FPR95: 12.34 -> 11.86No clear effect
increase samples per class for subspace from 5 to 20 (ablation)GradOrth · CIFAR-10avg FPR95: 12.34 -> 11.90No clear effect
increase samples per class for subspace from 5 to 40 (ablation)GradOrth · CIFAR-100avg FPR95: 33.35 -> 32.92No clear effect
increase samples per class for subspace from 5 to 10 (ablation)GradOrth · CIFAR-100avg FPR95: 33.35 -> 33.34No clear effect
use L2 norm instead of other Lp norms (L1, L3, L4, fraction) (ablation)GradOrth · ImageNetFPR95 and AUROCImproved
use L-infinity norm instead of L2 (ablation)GradOrth · ImageNetFPR95 and AUROCHurt
fractional norm (p=0.3) instead of L2 (ablation)GradOrth · ImageNetFPR95 and AUROCNo clear effect

Later papers that compared with this method

2 later accepted papers report GradOrth as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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