AI Paper Atlas

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

A Revisit of Sparse Coding Based Anomaly Detection in Stacked RNN Framework

Weixin Luo, Wen Liu, Shenghua Gao

ICCV 2017 · Label-efficient and robust learning › OOD and anomaly detection · approach: Deep one-class and tabular anomaly detection · 988 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
learn all parameters in a stacked RNN instead of fixed-hyperparameter sparse coding (TSC)TSC · UCSD Ped2frame-level AUC: 91.03% -> 92.21%Improved
learn all parameters in a stacked RNN instead of TSCTSC · CUHK Avenueframe-level AUC: 80.56% -> 81.71%Improved
learn all parameters in a stacked RNN instead of TSCTSC · ShanghaiTech Campusframe-level AUC: 67.94% -> 68.00%No clear effect
use sRNN instead of Conv-AEsRNN · UCSD Ped2frame-level AUC: 81.1% -> 92.21%Improved
use sRNN instead of Conv-AEsRNN · Moving-MNIST (synthetic)frame-level AUC: 74.3% -> 86.52%Improved
use TSC instead of Conv-AETSC · ShanghaiTech Campusframe-level AUC: 60.85% -> 67.94%Improved
use sRNN instead of ConvLSTM auto-encodersRNN · UCSD Ped2frame-level AUC: 88.10% -> 92.21%Improved
use sRNN instead of LSTM auto-encodersRNN · CUHK Avenueframe-level AUC: 75.33% -> 81.71%Improved
increase stacked RNN layers from 3 to 30 (more sparsity) (ablation)sRNN · UCSD Ped2frame-level AUC: 91.03% -> 88.10%Hurt
increase sparsity from 80.0% to 92.7% via more layers (ablation)sRNN · UCSD Ped2sparsity: 80.0% -> 92.7%Mixed
use a small temporal coherence weight lambda2 (ablation)TSC · Avenue and Ped2frame-level AUCHurt
increase sparsity weight lambda1 (ablation)TSC · Avenue and Ped2frame-level AUCNo 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