AI Paper Atlas

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

Few-Shot Scene-Adaptive Anomaly Detection

Yiwei Lu, Frank Yu, Mahesh Kumar Krishna Reddy, Yang Wang

ECCV 2020 · Label-efficient and robust learning › OOD and anomaly detection · approach: Unified multi-class anomaly detection · 171 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 MAML-based scene adaptation instead of fine-tuningr-GAN · Shanghai Tech 7 scenes, K=10AUC (%): 71.59 -> 77.36Improved
add MAML-based scene adaptation instead of fine-tuningr-GAN · Shanghai Tech 7 scenes, K=1AUC (%): 71.61 -> 74.51Improved
add MAML meta-learning rather than fine-tuning, cross-dataset (UCF crime meta-training)r-GAN · UCSD Ped2, K=1AUC (%): 65.58 -> 83.08Improved
add MAML adaptation rather than fine-tuning, cross-datasetr-GAN · UR Fall depth images, K=10 (Shanghai Tech meta-training)AUC (%): 62.89 -> 83.24Improved
adapt to the target scene with K frames versus no adaptation (fine-tuning)r-GAN pre-trained · UR Fall, K=10 (Shanghai Tech meta-training)AUC (%): 64.08 -> 62.89No clear effect
sample 5 tasks per epoch instead of 1 during meta-training (ablation)MAML scene-adaptive · UCSD Ped1, K=1AUC (%): 79.94 -> 80.6Improved
sample 5 tasks per epoch instead of 1 (ablation)MAML scene-adaptive · CUHK Avenue, K=10AUC (%): 77.31 -> 78.79Improved
sample 1 task per epoch instead of fine-tuning (ablation)MAML scene-adaptive · UCSD Ped2, K=1AUC (%): 85.64 -> 90.73Improved
use the GAN-based backbone r-GAN instead of r-VAEbackbone · Shanghai Tech (standard)AUC (%): 72.7 -> 77.9Improved
use more shots K from 1 to 10 for fine-tuning baselineFine-tuned baseline · Shanghai Tech 7 scenesAUC (%): 71.61 -> 71.59No 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