AI Paper Atlas

Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning

Reconstruction Guided Meta-Learning for Few Shot Open Set Recognition

Sayak Nag, Dripta S. Raychaudhuri, Sujoy Paul, Amit K. Roy–Chowdhury

TPAMI 2023 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Alignment-based few-shot metric learning · 27 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 VAE instead of autoencoder for reconstruction (ablation)ReFOCS · GTSRB->TT100K 5-way 5-shotAUROC: 77.08 -> 85.25Improved
use exemplar-weighted prototype instead of simple centroid (ablation)ReFOCS · GTSRB->TT100K 5-way 5-shotaccuracy: 81.79 -> 83.36Improved
use exemplar-weighted prototype instead of simple centroid (ablation)ReFOCS · GTSRB->TT100K 5-way 5-shotAUROC: 84.93 -> 85.25Improved
add embedding modulation (ablation)ReFOCS · Belga->Flickr32 5-way 1-shotAUROC: 56.69 -> 72.98Improved
add exemplar reconstruction errors as detector input (ablation)ReFOCS · Belga->Flickr32 5-way 1-shotAUROC: 50.01 -> 72.98Improved
add embedding as detector input (ablation)ReFOCS · GTSRB->TT100K 5-way 5-shotAUROC: 74.33 -> 85.25Improved
add classification score as detector input (ablation)ReFOCS · GTSRB->TT100K 5-way 5-shotAUROC: 82.85 -> 85.25Improved
use cosine instead of Euclidean distance (ablation)ReFOCS · Belga->Flickr32 5-way 1-shotAUROC: 50.61 -> 72.9Improved
use cosine instead of Euclidean distance (ablation)ReFOCS · miniImageNet 5-way 5-shot (Resnet18)accuracy: 79.09 vs 79.06No clear effect
use canonical instead of estimated exemplarsReFOCS · GTSRB->TT100K 5-way 5-shotAUROC: 79.48 -> 85.25Improved
use ReFOCS instead of PEELERReFOCS · GTSRB->TT100K (openness 29.3%)F1: 40.28 -> 52.31Improved
use ReFOCS instead of PEELERReFOCS · Belga->Flickr32 5-way 1-shot (openness 0%)F1: 48.91 -> 53.65Improved

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