AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Hybrid Models for Open Set Recognition

Hongjie Zhang, Ang Li, Jie Guo, Yanwen Guo

ECCV 2020 · Label-efficient and robust learning › Recognition and long-tail · approach: Learning from unlabeled and positive-unlabeled data · 163 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
train encoder jointly with classifier and flow instead of pretrained frozen encoder (ablation)OpenHybrid · MNIST/SVHN/CIFAR10F-score: 0.847 -> 0.942 (MNIST), 0.842 -> 0.912 (SVHN), 0.791 -> 0.865 (CIFAR10)Improved
joint training instead of pretrained encoder (ablation)OpenHybrid · TinyImageNetF-score: 0.674 -> 0.753Improved
joint training instead of pretrained encoder (ablation)OpenHybrid · CIFAR+10 / CIFAR+50F-score: 0.783 -> 0.903 (CIFAR+10), 0.761 -> 0.888 (CIFAR+50)Improved
learn embedding jointly with flow density estimator instead of flow on raw-embedding baselines (DIGLM)OpenHybrid · CIFAR10AUROC: 0.583 -> 0.950Improved
add outlier exposure to DIGLMDIGLM · CIFAR10AUROC: 0.583 -> 0.655Improved
OpenHybrid versus DIGLM+OE in F-scoreOpenHybrid · CIFAR10F-score: 0.701 -> 0.865Improved
increase trade-off lambda from 0.5 to 2 (ablation)OpenHybrid · MNISTAUROC: 0.993, 0.995, 0.998 for lambda 0.5, 1, 2No clear effect
increase number of residual blocks from 4 to 16 (ablation)OpenHybrid · CIFAR10AUROC: 0.945, 0.948, 0.950, 0.958 for 4, 8, 10, 16 blocksNo clear effect
compare against outlier exposure on cross-dataset OOD CIFAR10 -> CIFAR100OpenHybrid · CIFAR10 -> CIFAR100AUROC: 0.933 -> 0.951Improved
compare against outlier exposure on CIFAR100 -> CIFAR10OpenHybrid · CIFAR100 -> CIFAR10AUROC: 0.757 -> 0.856Improved
use full CIFAR10 as known and SVHN as unknownOpenHybrid · CIFAR10 vs SVHNAUROCImproved

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