AI Paper Atlas

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

Where's Wally Now? Deep Generative and Discriminative Embeddings for Novelty Detection

CVPR 2019 · Detection and segmentation › Open-set and few-shot detection · approach: Few-shot object detection · 52 citations (OpenAlex)

Check your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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 1CSVM on the GAN latent embedding instead of GANOMALYGenerative novelty detection · CIFAR-10 (MISO)AUC: 0.5321 (0.1292) -> 0.5627 (0.1458)Helped
Use 1CSVM on the GAN latent embedding instead of GANOMALYGenerative novelty detection · CIFAR-10 (SIMO)AUC: 0.6228 (0.1092) -> 0.6279 (0.1266)Helped
Use 1CSVM on the GAN latent embedding instead of GANOMALYGenerative novelty detection · IN-125 (MISO)AUC: 0.5708 (0.0775) -> 0.5792 (0.0719)Helped
Evaluate novelty detection across problem-complexity levels using BERCANovelty detection evaluation · IN-125 (MISO)AUCHelped
Use KL divergence (KLCA) as the empirical complexity measureNovelty detection evaluation · IN-125 (MISO)correlation with detection performanceHurt
Increase BERCA problem complexityDeep-embedding novelty detection methods · IN-125 (MISO)AUCHurt
Use LOF on GAP features as BERCA complexity increasesLOF/XGAP 512 · IN-125 (MISO)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