AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

Transfer-Based Semantic Anomaly Detection

Lucas Deecke, Lukas Ruff, Robert A. Vandermeulen, Hakan Bilen

ICML 2021 · Detection and segmentation › Open-set and few-shot detection · approach: Industrial anomaly detection · 5 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 regularization toward pretrained ImageNet weights (inductive bias) to OE-based training (ablation)ADIB · STL-10 semantic ADmAP: 38.6 to 49.5 relative to pretrained no-reg (a2 vs ADIB)Improved
use HSC loss with L2 regularization instead of eq.(2) objective (ablation)semantic AD ablation · CIFAR-10 semantic ADmAP: 68.5 (a3) vs 74.6 (ADIB)Hurt
replace L2 regularization with EWC (ablation)ADIB · CIFAR-10 semantic ADmAP: 66.4 (a5) vs 74.6 (ADIB)Hurt
use pretrained init without regularization (vs random init) (ablation)semantic AD · CIFAR-10 semantic ADmAP: 60.3 to 64.9Improved
use OE and transfer with residual adaptation (ADRA) instead of SAD baseline on MPI3DADRA · MPI3D interventionsAUC: ADRA improves performance over SAD under all interventionsImproved
add outlier exposure (OE) to DSVDD (ablation)DSVDD · MPI3D color interventionAUC: 11.7 to 100.0Improved
use SVHN instead of CIFAR-100 as OE dataset (ablation)ADIB · CIFAR-10 one-versus-rest ADmAUC: 99.1 with CIFAR-100 vs 79.8 with SVHNHurt
transfer-based regularization (ADIB/ADRA) vs SAD on small-mode robustness (ablation)ADIB and ADRA · CIFAR-10 minor mode (ship/truck)relative AUC for secondary class: SAD decreases much faster than ADIB and ADRAImproved
adding pretrained-transfer inductive bias (ADRA/ADIB) to OE-based AD on CIFAR-10 one-vs-restADIB · CIFAR-10 one-versus-rest ADmAUC: 99.1 vs 96.3 (HSC)Improved
add hyperspherical radial loss (HSC) vs standard classifier loss on CIFAR-10 semantic ADHSC-based model · STL-10 semantic ADmAP: 27.7 (HSC no reg) vs 32.9 (a1 standard loss)No 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